Instructions to use shareit/chatbot-supervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shareit/chatbot-supervisor with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chatbot-supervisor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Training in progress, step 9000, 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:e64ab3a8520f4fd1478e8c87c177a7e5713485f1c6c7d6b4a39a33b19cfeaf89
|
| 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 sha256:9ccf1225ec583c4dc6c6e489906f8d3b9d560242d913e91d9f7cdf8726389183
|
| 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:ea11996454b5587fcf33ae0ab5cf14b2031bf5f53f8c2ed5a48e87de31e29c84
|
| 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 sha256:647cfa6bd0ff342fbe8c9720c57cbb156d70769cb46d5fcddbc066b8fdac5f34
|
| 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,
|
|
@@ -60908,6 +60908,2106 @@
|
|
| 60908 |
"learning_rate": 2.7012914542689244e-05,
|
| 60909 |
"loss": 0.7542,
|
| 60910 |
"step": 8700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60911 |
}
|
| 60912 |
],
|
| 60913 |
"logging_steps": 1,
|
|
@@ -60927,7 +63027,7 @@
|
|
| 60927 |
"attributes": {}
|
| 60928 |
}
|
| 60929 |
},
|
| 60930 |
-
"total_flos":
|
| 60931 |
"train_batch_size": 8,
|
| 60932 |
"trial_name": null,
|
| 60933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.250712250712251,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 60908 |
"learning_rate": 2.7012914542689244e-05,
|
| 60909 |
"loss": 0.7542,
|
| 60910 |
"step": 8700
|
| 60911 |
+
},
|
| 60912 |
+
{
|
| 60913 |
+
"epoch": 9.91054131054131,
|
| 60914 |
+
"grad_norm": 0.1618286669254303,
|
| 60915 |
+
"learning_rate": 2.7008270453733166e-05,
|
| 60916 |
+
"loss": 0.946,
|
| 60917 |
+
"step": 8701
|
| 60918 |
+
},
|
| 60919 |
+
{
|
| 60920 |
+
"epoch": 9.91168091168091,
|
| 60921 |
+
"grad_norm": 0.21714560687541962,
|
| 60922 |
+
"learning_rate": 2.7003626295024338e-05,
|
| 60923 |
+
"loss": 0.684,
|
| 60924 |
+
"step": 8702
|
| 60925 |
+
},
|
| 60926 |
+
{
|
| 60927 |
+
"epoch": 9.912820512820513,
|
| 60928 |
+
"grad_norm": 0.22912001609802246,
|
| 60929 |
+
"learning_rate": 2.699898206672405e-05,
|
| 60930 |
+
"loss": 0.7059,
|
| 60931 |
+
"step": 8703
|
| 60932 |
+
},
|
| 60933 |
+
{
|
| 60934 |
+
"epoch": 9.913960113960114,
|
| 60935 |
+
"grad_norm": 0.22242160141468048,
|
| 60936 |
+
"learning_rate": 2.6994337768993628e-05,
|
| 60937 |
+
"loss": 0.7202,
|
| 60938 |
+
"step": 8704
|
| 60939 |
+
},
|
| 60940 |
+
{
|
| 60941 |
+
"epoch": 9.915099715099714,
|
| 60942 |
+
"grad_norm": 0.20211511850357056,
|
| 60943 |
+
"learning_rate": 2.6989693401994353e-05,
|
| 60944 |
+
"loss": 0.7771,
|
| 60945 |
+
"step": 8705
|
| 60946 |
+
},
|
| 60947 |
+
{
|
| 60948 |
+
"epoch": 9.916239316239317,
|
| 60949 |
+
"grad_norm": 0.22866898775100708,
|
| 60950 |
+
"learning_rate": 2.698504896588757e-05,
|
| 60951 |
+
"loss": 0.6256,
|
| 60952 |
+
"step": 8706
|
| 60953 |
+
},
|
| 60954 |
+
{
|
| 60955 |
+
"epoch": 9.917378917378917,
|
| 60956 |
+
"grad_norm": 0.18713034689426422,
|
| 60957 |
+
"learning_rate": 2.6980404460834575e-05,
|
| 60958 |
+
"loss": 0.8939,
|
| 60959 |
+
"step": 8707
|
| 60960 |
+
},
|
| 60961 |
+
{
|
| 60962 |
+
"epoch": 9.918518518518518,
|
| 60963 |
+
"grad_norm": 0.22166401147842407,
|
| 60964 |
+
"learning_rate": 2.6975759886996688e-05,
|
| 60965 |
+
"loss": 0.638,
|
| 60966 |
+
"step": 8708
|
| 60967 |
+
},
|
| 60968 |
+
{
|
| 60969 |
+
"epoch": 9.91965811965812,
|
| 60970 |
+
"grad_norm": 0.19920535385608673,
|
| 60971 |
+
"learning_rate": 2.697111524453522e-05,
|
| 60972 |
+
"loss": 0.7802,
|
| 60973 |
+
"step": 8709
|
| 60974 |
+
},
|
| 60975 |
+
{
|
| 60976 |
+
"epoch": 9.92079772079772,
|
| 60977 |
+
"grad_norm": 0.22823186218738556,
|
| 60978 |
+
"learning_rate": 2.69664705336115e-05,
|
| 60979 |
+
"loss": 0.6718,
|
| 60980 |
+
"step": 8710
|
| 60981 |
+
},
|
| 60982 |
+
{
|
| 60983 |
+
"epoch": 9.921937321937321,
|
| 60984 |
+
"grad_norm": 0.19130191206932068,
|
| 60985 |
+
"learning_rate": 2.696182575438686e-05,
|
| 60986 |
+
"loss": 0.8057,
|
| 60987 |
+
"step": 8711
|
| 60988 |
+
},
|
| 60989 |
+
{
|
| 60990 |
+
"epoch": 9.923076923076923,
|
| 60991 |
+
"grad_norm": 0.18313159048557281,
|
| 60992 |
+
"learning_rate": 2.6957180907022604e-05,
|
| 60993 |
+
"loss": 0.7729,
|
| 60994 |
+
"step": 8712
|
| 60995 |
+
},
|
| 60996 |
+
{
|
| 60997 |
+
"epoch": 9.924216524216524,
|
| 60998 |
+
"grad_norm": 0.18810537457466125,
|
| 60999 |
+
"learning_rate": 2.6952535991680085e-05,
|
| 61000 |
+
"loss": 0.5622,
|
| 61001 |
+
"step": 8713
|
| 61002 |
+
},
|
| 61003 |
+
{
|
| 61004 |
+
"epoch": 9.925356125356124,
|
| 61005 |
+
"grad_norm": 0.21185599267482758,
|
| 61006 |
+
"learning_rate": 2.6947891008520615e-05,
|
| 61007 |
+
"loss": 0.8193,
|
| 61008 |
+
"step": 8714
|
| 61009 |
+
},
|
| 61010 |
+
{
|
| 61011 |
+
"epoch": 9.926495726495727,
|
| 61012 |
+
"grad_norm": 0.19980546832084656,
|
| 61013 |
+
"learning_rate": 2.6943245957705536e-05,
|
| 61014 |
+
"loss": 0.6878,
|
| 61015 |
+
"step": 8715
|
| 61016 |
+
},
|
| 61017 |
+
{
|
| 61018 |
+
"epoch": 9.927635327635327,
|
| 61019 |
+
"grad_norm": 0.21896570920944214,
|
| 61020 |
+
"learning_rate": 2.6938600839396173e-05,
|
| 61021 |
+
"loss": 0.6131,
|
| 61022 |
+
"step": 8716
|
| 61023 |
+
},
|
| 61024 |
+
{
|
| 61025 |
+
"epoch": 9.928774928774928,
|
| 61026 |
+
"grad_norm": 0.2273005247116089,
|
| 61027 |
+
"learning_rate": 2.693395565375388e-05,
|
| 61028 |
+
"loss": 0.705,
|
| 61029 |
+
"step": 8717
|
| 61030 |
+
},
|
| 61031 |
+
{
|
| 61032 |
+
"epoch": 9.92991452991453,
|
| 61033 |
+
"grad_norm": 0.1967950165271759,
|
| 61034 |
+
"learning_rate": 2.6929310400939983e-05,
|
| 61035 |
+
"loss": 0.8488,
|
| 61036 |
+
"step": 8718
|
| 61037 |
+
},
|
| 61038 |
+
{
|
| 61039 |
+
"epoch": 9.93105413105413,
|
| 61040 |
+
"grad_norm": 0.22161847352981567,
|
| 61041 |
+
"learning_rate": 2.692466508111584e-05,
|
| 61042 |
+
"loss": 0.5494,
|
| 61043 |
+
"step": 8719
|
| 61044 |
+
},
|
| 61045 |
+
{
|
| 61046 |
+
"epoch": 9.932193732193731,
|
| 61047 |
+
"grad_norm": 0.2432965487241745,
|
| 61048 |
+
"learning_rate": 2.6920019694442776e-05,
|
| 61049 |
+
"loss": 0.6465,
|
| 61050 |
+
"step": 8720
|
| 61051 |
+
},
|
| 61052 |
+
{
|
| 61053 |
+
"epoch": 9.933333333333334,
|
| 61054 |
+
"grad_norm": 0.23050159215927124,
|
| 61055 |
+
"learning_rate": 2.6915374241082157e-05,
|
| 61056 |
+
"loss": 0.6693,
|
| 61057 |
+
"step": 8721
|
| 61058 |
+
},
|
| 61059 |
+
{
|
| 61060 |
+
"epoch": 9.934472934472934,
|
| 61061 |
+
"grad_norm": 0.19228944182395935,
|
| 61062 |
+
"learning_rate": 2.691072872119531e-05,
|
| 61063 |
+
"loss": 0.8071,
|
| 61064 |
+
"step": 8722
|
| 61065 |
+
},
|
| 61066 |
+
{
|
| 61067 |
+
"epoch": 9.935612535612536,
|
| 61068 |
+
"grad_norm": 0.21512329578399658,
|
| 61069 |
+
"learning_rate": 2.690608313494361e-05,
|
| 61070 |
+
"loss": 0.6593,
|
| 61071 |
+
"step": 8723
|
| 61072 |
+
},
|
| 61073 |
+
{
|
| 61074 |
+
"epoch": 9.936752136752137,
|
| 61075 |
+
"grad_norm": 0.1586693525314331,
|
| 61076 |
+
"learning_rate": 2.6901437482488396e-05,
|
| 61077 |
+
"loss": 0.7464,
|
| 61078 |
+
"step": 8724
|
| 61079 |
+
},
|
| 61080 |
+
{
|
| 61081 |
+
"epoch": 9.937891737891738,
|
| 61082 |
+
"grad_norm": 0.21485713124275208,
|
| 61083 |
+
"learning_rate": 2.6896791763991035e-05,
|
| 61084 |
+
"loss": 0.8258,
|
| 61085 |
+
"step": 8725
|
| 61086 |
+
},
|
| 61087 |
+
{
|
| 61088 |
+
"epoch": 9.93903133903134,
|
| 61089 |
+
"grad_norm": 0.1861257255077362,
|
| 61090 |
+
"learning_rate": 2.6892145979612875e-05,
|
| 61091 |
+
"loss": 0.7165,
|
| 61092 |
+
"step": 8726
|
| 61093 |
+
},
|
| 61094 |
+
{
|
| 61095 |
+
"epoch": 9.94017094017094,
|
| 61096 |
+
"grad_norm": 0.2221956104040146,
|
| 61097 |
+
"learning_rate": 2.6887500129515288e-05,
|
| 61098 |
+
"loss": 0.6439,
|
| 61099 |
+
"step": 8727
|
| 61100 |
+
},
|
| 61101 |
+
{
|
| 61102 |
+
"epoch": 9.941310541310541,
|
| 61103 |
+
"grad_norm": 0.1893671303987503,
|
| 61104 |
+
"learning_rate": 2.6882854213859628e-05,
|
| 61105 |
+
"loss": 0.7803,
|
| 61106 |
+
"step": 8728
|
| 61107 |
+
},
|
| 61108 |
+
{
|
| 61109 |
+
"epoch": 9.942450142450143,
|
| 61110 |
+
"grad_norm": 0.22396253049373627,
|
| 61111 |
+
"learning_rate": 2.6878208232807254e-05,
|
| 61112 |
+
"loss": 0.63,
|
| 61113 |
+
"step": 8729
|
| 61114 |
+
},
|
| 61115 |
+
{
|
| 61116 |
+
"epoch": 9.943589743589744,
|
| 61117 |
+
"grad_norm": 0.2166588455438614,
|
| 61118 |
+
"learning_rate": 2.6873562186519558e-05,
|
| 61119 |
+
"loss": 0.6246,
|
| 61120 |
+
"step": 8730
|
| 61121 |
+
},
|
| 61122 |
+
{
|
| 61123 |
+
"epoch": 9.944729344729344,
|
| 61124 |
+
"grad_norm": 0.18603435158729553,
|
| 61125 |
+
"learning_rate": 2.6868916075157884e-05,
|
| 61126 |
+
"loss": 0.5585,
|
| 61127 |
+
"step": 8731
|
| 61128 |
+
},
|
| 61129 |
+
{
|
| 61130 |
+
"epoch": 9.945868945868947,
|
| 61131 |
+
"grad_norm": 0.18738475441932678,
|
| 61132 |
+
"learning_rate": 2.686426989888362e-05,
|
| 61133 |
+
"loss": 0.7881,
|
| 61134 |
+
"step": 8732
|
| 61135 |
+
},
|
| 61136 |
+
{
|
| 61137 |
+
"epoch": 9.947008547008547,
|
| 61138 |
+
"grad_norm": 0.24822686612606049,
|
| 61139 |
+
"learning_rate": 2.685962365785813e-05,
|
| 61140 |
+
"loss": 0.6375,
|
| 61141 |
+
"step": 8733
|
| 61142 |
+
},
|
| 61143 |
+
{
|
| 61144 |
+
"epoch": 9.948148148148148,
|
| 61145 |
+
"grad_norm": 0.21976767480373383,
|
| 61146 |
+
"learning_rate": 2.6854977352242805e-05,
|
| 61147 |
+
"loss": 0.703,
|
| 61148 |
+
"step": 8734
|
| 61149 |
+
},
|
| 61150 |
+
{
|
| 61151 |
+
"epoch": 9.94928774928775,
|
| 61152 |
+
"grad_norm": 0.22957386076450348,
|
| 61153 |
+
"learning_rate": 2.6850330982199007e-05,
|
| 61154 |
+
"loss": 0.6039,
|
| 61155 |
+
"step": 8735
|
| 61156 |
+
},
|
| 61157 |
+
{
|
| 61158 |
+
"epoch": 9.95042735042735,
|
| 61159 |
+
"grad_norm": 0.19751594960689545,
|
| 61160 |
+
"learning_rate": 2.6845684547888133e-05,
|
| 61161 |
+
"loss": 0.8182,
|
| 61162 |
+
"step": 8736
|
| 61163 |
+
},
|
| 61164 |
+
{
|
| 61165 |
+
"epoch": 9.951566951566951,
|
| 61166 |
+
"grad_norm": 0.23954753577709198,
|
| 61167 |
+
"learning_rate": 2.6841038049471556e-05,
|
| 61168 |
+
"loss": 0.6498,
|
| 61169 |
+
"step": 8737
|
| 61170 |
+
},
|
| 61171 |
+
{
|
| 61172 |
+
"epoch": 9.952706552706553,
|
| 61173 |
+
"grad_norm": 0.19721907377243042,
|
| 61174 |
+
"learning_rate": 2.6836391487110662e-05,
|
| 61175 |
+
"loss": 0.7403,
|
| 61176 |
+
"step": 8738
|
| 61177 |
+
},
|
| 61178 |
+
{
|
| 61179 |
+
"epoch": 9.953846153846154,
|
| 61180 |
+
"grad_norm": 0.2065429985523224,
|
| 61181 |
+
"learning_rate": 2.6831744860966846e-05,
|
| 61182 |
+
"loss": 0.7021,
|
| 61183 |
+
"step": 8739
|
| 61184 |
+
},
|
| 61185 |
+
{
|
| 61186 |
+
"epoch": 9.954985754985755,
|
| 61187 |
+
"grad_norm": 0.2047637403011322,
|
| 61188 |
+
"learning_rate": 2.6827098171201493e-05,
|
| 61189 |
+
"loss": 0.7156,
|
| 61190 |
+
"step": 8740
|
| 61191 |
+
},
|
| 61192 |
+
{
|
| 61193 |
+
"epoch": 9.956125356125357,
|
| 61194 |
+
"grad_norm": 0.24892592430114746,
|
| 61195 |
+
"learning_rate": 2.6822451417975996e-05,
|
| 61196 |
+
"loss": 0.4964,
|
| 61197 |
+
"step": 8741
|
| 61198 |
+
},
|
| 61199 |
+
{
|
| 61200 |
+
"epoch": 9.957264957264957,
|
| 61201 |
+
"grad_norm": 0.25440195202827454,
|
| 61202 |
+
"learning_rate": 2.6817804601451747e-05,
|
| 61203 |
+
"loss": 0.4231,
|
| 61204 |
+
"step": 8742
|
| 61205 |
+
},
|
| 61206 |
+
{
|
| 61207 |
+
"epoch": 9.958404558404558,
|
| 61208 |
+
"grad_norm": 0.21469826996326447,
|
| 61209 |
+
"learning_rate": 2.6813157721790146e-05,
|
| 61210 |
+
"loss": 0.6043,
|
| 61211 |
+
"step": 8743
|
| 61212 |
+
},
|
| 61213 |
+
{
|
| 61214 |
+
"epoch": 9.95954415954416,
|
| 61215 |
+
"grad_norm": 0.20514146983623505,
|
| 61216 |
+
"learning_rate": 2.680851077915259e-05,
|
| 61217 |
+
"loss": 0.9217,
|
| 61218 |
+
"step": 8744
|
| 61219 |
+
},
|
| 61220 |
+
{
|
| 61221 |
+
"epoch": 9.96068376068376,
|
| 61222 |
+
"grad_norm": 0.19511772692203522,
|
| 61223 |
+
"learning_rate": 2.6803863773700482e-05,
|
| 61224 |
+
"loss": 0.7281,
|
| 61225 |
+
"step": 8745
|
| 61226 |
+
},
|
| 61227 |
+
{
|
| 61228 |
+
"epoch": 9.961823361823361,
|
| 61229 |
+
"grad_norm": 0.16267132759094238,
|
| 61230 |
+
"learning_rate": 2.6799216705595226e-05,
|
| 61231 |
+
"loss": 0.6238,
|
| 61232 |
+
"step": 8746
|
| 61233 |
+
},
|
| 61234 |
+
{
|
| 61235 |
+
"epoch": 9.962962962962964,
|
| 61236 |
+
"grad_norm": 0.19934651255607605,
|
| 61237 |
+
"learning_rate": 2.679456957499823e-05,
|
| 61238 |
+
"loss": 0.7066,
|
| 61239 |
+
"step": 8747
|
| 61240 |
+
},
|
| 61241 |
+
{
|
| 61242 |
+
"epoch": 9.964102564102564,
|
| 61243 |
+
"grad_norm": 0.14993909001350403,
|
| 61244 |
+
"learning_rate": 2.6789922382070887e-05,
|
| 61245 |
+
"loss": 1.0104,
|
| 61246 |
+
"step": 8748
|
| 61247 |
+
},
|
| 61248 |
+
{
|
| 61249 |
+
"epoch": 9.965242165242165,
|
| 61250 |
+
"grad_norm": 0.19606129825115204,
|
| 61251 |
+
"learning_rate": 2.6785275126974624e-05,
|
| 61252 |
+
"loss": 0.6397,
|
| 61253 |
+
"step": 8749
|
| 61254 |
+
},
|
| 61255 |
+
{
|
| 61256 |
+
"epoch": 9.966381766381767,
|
| 61257 |
+
"grad_norm": 0.19740979373455048,
|
| 61258 |
+
"learning_rate": 2.678062780987084e-05,
|
| 61259 |
+
"loss": 0.6837,
|
| 61260 |
+
"step": 8750
|
| 61261 |
+
},
|
| 61262 |
+
{
|
| 61263 |
+
"epoch": 9.967521367521368,
|
| 61264 |
+
"grad_norm": 0.24982787668704987,
|
| 61265 |
+
"learning_rate": 2.6775980430920966e-05,
|
| 61266 |
+
"loss": 0.6456,
|
| 61267 |
+
"step": 8751
|
| 61268 |
+
},
|
| 61269 |
+
{
|
| 61270 |
+
"epoch": 9.968660968660968,
|
| 61271 |
+
"grad_norm": 0.20626413822174072,
|
| 61272 |
+
"learning_rate": 2.67713329902864e-05,
|
| 61273 |
+
"loss": 0.6292,
|
| 61274 |
+
"step": 8752
|
| 61275 |
+
},
|
| 61276 |
+
{
|
| 61277 |
+
"epoch": 9.96980056980057,
|
| 61278 |
+
"grad_norm": 0.16925214231014252,
|
| 61279 |
+
"learning_rate": 2.6766685488128572e-05,
|
| 61280 |
+
"loss": 0.8886,
|
| 61281 |
+
"step": 8753
|
| 61282 |
+
},
|
| 61283 |
+
{
|
| 61284 |
+
"epoch": 9.970940170940171,
|
| 61285 |
+
"grad_norm": 0.23425494134426117,
|
| 61286 |
+
"learning_rate": 2.6762037924608897e-05,
|
| 61287 |
+
"loss": 0.6506,
|
| 61288 |
+
"step": 8754
|
| 61289 |
+
},
|
| 61290 |
+
{
|
| 61291 |
+
"epoch": 9.972079772079772,
|
| 61292 |
+
"grad_norm": 0.1767222136259079,
|
| 61293 |
+
"learning_rate": 2.6757390299888795e-05,
|
| 61294 |
+
"loss": 0.802,
|
| 61295 |
+
"step": 8755
|
| 61296 |
+
},
|
| 61297 |
+
{
|
| 61298 |
+
"epoch": 9.973219373219374,
|
| 61299 |
+
"grad_norm": 0.2280825823545456,
|
| 61300 |
+
"learning_rate": 2.6752742614129706e-05,
|
| 61301 |
+
"loss": 0.7288,
|
| 61302 |
+
"step": 8756
|
| 61303 |
+
},
|
| 61304 |
+
{
|
| 61305 |
+
"epoch": 9.974358974358974,
|
| 61306 |
+
"grad_norm": 0.2023814171552658,
|
| 61307 |
+
"learning_rate": 2.674809486749304e-05,
|
| 61308 |
+
"loss": 0.7595,
|
| 61309 |
+
"step": 8757
|
| 61310 |
+
},
|
| 61311 |
+
{
|
| 61312 |
+
"epoch": 9.975498575498575,
|
| 61313 |
+
"grad_norm": 0.2898479402065277,
|
| 61314 |
+
"learning_rate": 2.674344706014023e-05,
|
| 61315 |
+
"loss": 0.6536,
|
| 61316 |
+
"step": 8758
|
| 61317 |
+
},
|
| 61318 |
+
{
|
| 61319 |
+
"epoch": 9.976638176638177,
|
| 61320 |
+
"grad_norm": 0.25874680280685425,
|
| 61321 |
+
"learning_rate": 2.673879919223271e-05,
|
| 61322 |
+
"loss": 0.5329,
|
| 61323 |
+
"step": 8759
|
| 61324 |
+
},
|
| 61325 |
+
{
|
| 61326 |
+
"epoch": 9.977777777777778,
|
| 61327 |
+
"grad_norm": 0.20675835013389587,
|
| 61328 |
+
"learning_rate": 2.673415126393191e-05,
|
| 61329 |
+
"loss": 0.945,
|
| 61330 |
+
"step": 8760
|
| 61331 |
+
},
|
| 61332 |
+
{
|
| 61333 |
+
"epoch": 9.978917378917378,
|
| 61334 |
+
"grad_norm": 0.23534797132015228,
|
| 61335 |
+
"learning_rate": 2.672950327539927e-05,
|
| 61336 |
+
"loss": 0.6476,
|
| 61337 |
+
"step": 8761
|
| 61338 |
+
},
|
| 61339 |
+
{
|
| 61340 |
+
"epoch": 9.98005698005698,
|
| 61341 |
+
"grad_norm": 0.2391483187675476,
|
| 61342 |
+
"learning_rate": 2.6724855226796232e-05,
|
| 61343 |
+
"loss": 0.6501,
|
| 61344 |
+
"step": 8762
|
| 61345 |
+
},
|
| 61346 |
+
{
|
| 61347 |
+
"epoch": 9.981196581196581,
|
| 61348 |
+
"grad_norm": 0.2711732089519501,
|
| 61349 |
+
"learning_rate": 2.672020711828422e-05,
|
| 61350 |
+
"loss": 0.6641,
|
| 61351 |
+
"step": 8763
|
| 61352 |
+
},
|
| 61353 |
+
{
|
| 61354 |
+
"epoch": 9.982336182336182,
|
| 61355 |
+
"grad_norm": 0.2136969417333603,
|
| 61356 |
+
"learning_rate": 2.6715558950024687e-05,
|
| 61357 |
+
"loss": 0.8328,
|
| 61358 |
+
"step": 8764
|
| 61359 |
+
},
|
| 61360 |
+
{
|
| 61361 |
+
"epoch": 9.983475783475784,
|
| 61362 |
+
"grad_norm": 0.18608087301254272,
|
| 61363 |
+
"learning_rate": 2.6710910722179074e-05,
|
| 61364 |
+
"loss": 0.6553,
|
| 61365 |
+
"step": 8765
|
| 61366 |
+
},
|
| 61367 |
+
{
|
| 61368 |
+
"epoch": 9.984615384615385,
|
| 61369 |
+
"grad_norm": 0.1654229313135147,
|
| 61370 |
+
"learning_rate": 2.6706262434908818e-05,
|
| 61371 |
+
"loss": 0.6155,
|
| 61372 |
+
"step": 8766
|
| 61373 |
+
},
|
| 61374 |
+
{
|
| 61375 |
+
"epoch": 9.985754985754985,
|
| 61376 |
+
"grad_norm": 0.18682758510112762,
|
| 61377 |
+
"learning_rate": 2.6701614088375383e-05,
|
| 61378 |
+
"loss": 0.6275,
|
| 61379 |
+
"step": 8767
|
| 61380 |
+
},
|
| 61381 |
+
{
|
| 61382 |
+
"epoch": 9.986894586894588,
|
| 61383 |
+
"grad_norm": 0.25929149985313416,
|
| 61384 |
+
"learning_rate": 2.6696965682740217e-05,
|
| 61385 |
+
"loss": 0.5789,
|
| 61386 |
+
"step": 8768
|
| 61387 |
+
},
|
| 61388 |
+
{
|
| 61389 |
+
"epoch": 9.988034188034188,
|
| 61390 |
+
"grad_norm": 0.22134925425052643,
|
| 61391 |
+
"learning_rate": 2.669231721816476e-05,
|
| 61392 |
+
"loss": 0.5432,
|
| 61393 |
+
"step": 8769
|
| 61394 |
+
},
|
| 61395 |
+
{
|
| 61396 |
+
"epoch": 9.989173789173789,
|
| 61397 |
+
"grad_norm": 0.19857807457447052,
|
| 61398 |
+
"learning_rate": 2.6687668694810475e-05,
|
| 61399 |
+
"loss": 0.852,
|
| 61400 |
+
"step": 8770
|
| 61401 |
+
},
|
| 61402 |
+
{
|
| 61403 |
+
"epoch": 9.990313390313391,
|
| 61404 |
+
"grad_norm": 0.22108644247055054,
|
| 61405 |
+
"learning_rate": 2.668302011283881e-05,
|
| 61406 |
+
"loss": 0.8514,
|
| 61407 |
+
"step": 8771
|
| 61408 |
+
},
|
| 61409 |
+
{
|
| 61410 |
+
"epoch": 9.991452991452991,
|
| 61411 |
+
"grad_norm": 0.19870635867118835,
|
| 61412 |
+
"learning_rate": 2.667837147241123e-05,
|
| 61413 |
+
"loss": 0.6856,
|
| 61414 |
+
"step": 8772
|
| 61415 |
+
},
|
| 61416 |
+
{
|
| 61417 |
+
"epoch": 9.992592592592592,
|
| 61418 |
+
"grad_norm": 0.24190519750118256,
|
| 61419 |
+
"learning_rate": 2.6673722773689196e-05,
|
| 61420 |
+
"loss": 0.4523,
|
| 61421 |
+
"step": 8773
|
| 61422 |
+
},
|
| 61423 |
+
{
|
| 61424 |
+
"epoch": 9.993732193732194,
|
| 61425 |
+
"grad_norm": 0.19627119600772858,
|
| 61426 |
+
"learning_rate": 2.666907401683416e-05,
|
| 61427 |
+
"loss": 1.0093,
|
| 61428 |
+
"step": 8774
|
| 61429 |
+
},
|
| 61430 |
+
{
|
| 61431 |
+
"epoch": 9.994871794871795,
|
| 61432 |
+
"grad_norm": 0.1963256150484085,
|
| 61433 |
+
"learning_rate": 2.6664425202007604e-05,
|
| 61434 |
+
"loss": 0.814,
|
| 61435 |
+
"step": 8775
|
| 61436 |
+
},
|
| 61437 |
+
{
|
| 61438 |
+
"epoch": 9.996011396011395,
|
| 61439 |
+
"grad_norm": 0.2213260382413864,
|
| 61440 |
+
"learning_rate": 2.6659776329370977e-05,
|
| 61441 |
+
"loss": 0.7355,
|
| 61442 |
+
"step": 8776
|
| 61443 |
+
},
|
| 61444 |
+
{
|
| 61445 |
+
"epoch": 9.997150997150998,
|
| 61446 |
+
"grad_norm": 0.2520917057991028,
|
| 61447 |
+
"learning_rate": 2.6655127399085755e-05,
|
| 61448 |
+
"loss": 0.4771,
|
| 61449 |
+
"step": 8777
|
| 61450 |
+
},
|
| 61451 |
+
{
|
| 61452 |
+
"epoch": 9.998290598290598,
|
| 61453 |
+
"grad_norm": 0.24032898247241974,
|
| 61454 |
+
"learning_rate": 2.6650478411313407e-05,
|
| 61455 |
+
"loss": 0.6357,
|
| 61456 |
+
"step": 8778
|
| 61457 |
+
},
|
| 61458 |
+
{
|
| 61459 |
+
"epoch": 9.999430199430199,
|
| 61460 |
+
"grad_norm": 0.18503084778785706,
|
| 61461 |
+
"learning_rate": 2.6645829366215407e-05,
|
| 61462 |
+
"loss": 0.586,
|
| 61463 |
+
"step": 8779
|
| 61464 |
+
},
|
| 61465 |
+
{
|
| 61466 |
+
"epoch": 10.0,
|
| 61467 |
+
"grad_norm": 0.554973840713501,
|
| 61468 |
+
"learning_rate": 2.6641180263953224e-05,
|
| 61469 |
+
"loss": 0.5772,
|
| 61470 |
+
"step": 8780
|
| 61471 |
+
},
|
| 61472 |
+
{
|
| 61473 |
+
"epoch": 10.0011396011396,
|
| 61474 |
+
"grad_norm": 0.27616214752197266,
|
| 61475 |
+
"learning_rate": 2.663653110468834e-05,
|
| 61476 |
+
"loss": 0.4348,
|
| 61477 |
+
"step": 8781
|
| 61478 |
+
},
|
| 61479 |
+
{
|
| 61480 |
+
"epoch": 10.002279202279203,
|
| 61481 |
+
"grad_norm": 0.21189844608306885,
|
| 61482 |
+
"learning_rate": 2.663188188858222e-05,
|
| 61483 |
+
"loss": 0.5661,
|
| 61484 |
+
"step": 8782
|
| 61485 |
+
},
|
| 61486 |
+
{
|
| 61487 |
+
"epoch": 10.003418803418803,
|
| 61488 |
+
"grad_norm": 0.19806593656539917,
|
| 61489 |
+
"learning_rate": 2.6627232615796367e-05,
|
| 61490 |
+
"loss": 0.7006,
|
| 61491 |
+
"step": 8783
|
| 61492 |
+
},
|
| 61493 |
+
{
|
| 61494 |
+
"epoch": 10.004558404558404,
|
| 61495 |
+
"grad_norm": 0.22303634881973267,
|
| 61496 |
+
"learning_rate": 2.6622583286492243e-05,
|
| 61497 |
+
"loss": 0.522,
|
| 61498 |
+
"step": 8784
|
| 61499 |
+
},
|
| 61500 |
+
{
|
| 61501 |
+
"epoch": 10.005698005698006,
|
| 61502 |
+
"grad_norm": 0.18687784671783447,
|
| 61503 |
+
"learning_rate": 2.661793390083135e-05,
|
| 61504 |
+
"loss": 0.7389,
|
| 61505 |
+
"step": 8785
|
| 61506 |
+
},
|
| 61507 |
+
{
|
| 61508 |
+
"epoch": 10.006837606837607,
|
| 61509 |
+
"grad_norm": 0.18081918358802795,
|
| 61510 |
+
"learning_rate": 2.661328445897515e-05,
|
| 61511 |
+
"loss": 0.7818,
|
| 61512 |
+
"step": 8786
|
| 61513 |
+
},
|
| 61514 |
+
{
|
| 61515 |
+
"epoch": 10.007977207977207,
|
| 61516 |
+
"grad_norm": 0.2659003436565399,
|
| 61517 |
+
"learning_rate": 2.6608634961085155e-05,
|
| 61518 |
+
"loss": 0.5833,
|
| 61519 |
+
"step": 8787
|
| 61520 |
+
},
|
| 61521 |
+
{
|
| 61522 |
+
"epoch": 10.00911680911681,
|
| 61523 |
+
"grad_norm": 0.18005883693695068,
|
| 61524 |
+
"learning_rate": 2.6603985407322834e-05,
|
| 61525 |
+
"loss": 0.8288,
|
| 61526 |
+
"step": 8788
|
| 61527 |
+
},
|
| 61528 |
+
{
|
| 61529 |
+
"epoch": 10.01025641025641,
|
| 61530 |
+
"grad_norm": 0.21639782190322876,
|
| 61531 |
+
"learning_rate": 2.6599335797849695e-05,
|
| 61532 |
+
"loss": 0.6301,
|
| 61533 |
+
"step": 8789
|
| 61534 |
+
},
|
| 61535 |
+
{
|
| 61536 |
+
"epoch": 10.01139601139601,
|
| 61537 |
+
"grad_norm": 0.19014930725097656,
|
| 61538 |
+
"learning_rate": 2.6594686132827227e-05,
|
| 61539 |
+
"loss": 0.7667,
|
| 61540 |
+
"step": 8790
|
| 61541 |
+
},
|
| 61542 |
+
{
|
| 61543 |
+
"epoch": 10.012535612535613,
|
| 61544 |
+
"grad_norm": 0.22009646892547607,
|
| 61545 |
+
"learning_rate": 2.659003641241692e-05,
|
| 61546 |
+
"loss": 0.6251,
|
| 61547 |
+
"step": 8791
|
| 61548 |
+
},
|
| 61549 |
+
{
|
| 61550 |
+
"epoch": 10.013675213675214,
|
| 61551 |
+
"grad_norm": 0.24239443242549896,
|
| 61552 |
+
"learning_rate": 2.658538663678028e-05,
|
| 61553 |
+
"loss": 0.5819,
|
| 61554 |
+
"step": 8792
|
| 61555 |
+
},
|
| 61556 |
+
{
|
| 61557 |
+
"epoch": 10.014814814814814,
|
| 61558 |
+
"grad_norm": 0.20067726075649261,
|
| 61559 |
+
"learning_rate": 2.6580736806078792e-05,
|
| 61560 |
+
"loss": 0.7514,
|
| 61561 |
+
"step": 8793
|
| 61562 |
+
},
|
| 61563 |
+
{
|
| 61564 |
+
"epoch": 10.015954415954416,
|
| 61565 |
+
"grad_norm": 0.17462316155433655,
|
| 61566 |
+
"learning_rate": 2.657608692047398e-05,
|
| 61567 |
+
"loss": 0.8196,
|
| 61568 |
+
"step": 8794
|
| 61569 |
+
},
|
| 61570 |
+
{
|
| 61571 |
+
"epoch": 10.017094017094017,
|
| 61572 |
+
"grad_norm": 0.18429355323314667,
|
| 61573 |
+
"learning_rate": 2.657143698012733e-05,
|
| 61574 |
+
"loss": 0.7408,
|
| 61575 |
+
"step": 8795
|
| 61576 |
+
},
|
| 61577 |
+
{
|
| 61578 |
+
"epoch": 10.018233618233618,
|
| 61579 |
+
"grad_norm": 0.19342951476573944,
|
| 61580 |
+
"learning_rate": 2.6566786985200355e-05,
|
| 61581 |
+
"loss": 0.7168,
|
| 61582 |
+
"step": 8796
|
| 61583 |
+
},
|
| 61584 |
+
{
|
| 61585 |
+
"epoch": 10.01937321937322,
|
| 61586 |
+
"grad_norm": 0.25074589252471924,
|
| 61587 |
+
"learning_rate": 2.6562136935854553e-05,
|
| 61588 |
+
"loss": 0.61,
|
| 61589 |
+
"step": 8797
|
| 61590 |
+
},
|
| 61591 |
+
{
|
| 61592 |
+
"epoch": 10.02051282051282,
|
| 61593 |
+
"grad_norm": 0.2421872615814209,
|
| 61594 |
+
"learning_rate": 2.655748683225145e-05,
|
| 61595 |
+
"loss": 0.5853,
|
| 61596 |
+
"step": 8798
|
| 61597 |
+
},
|
| 61598 |
+
{
|
| 61599 |
+
"epoch": 10.021652421652421,
|
| 61600 |
+
"grad_norm": 0.19836491346359253,
|
| 61601 |
+
"learning_rate": 2.655283667455253e-05,
|
| 61602 |
+
"loss": 0.4798,
|
| 61603 |
+
"step": 8799
|
| 61604 |
+
},
|
| 61605 |
+
{
|
| 61606 |
+
"epoch": 10.022792022792023,
|
| 61607 |
+
"grad_norm": 0.2570490837097168,
|
| 61608 |
+
"learning_rate": 2.6548186462919334e-05,
|
| 61609 |
+
"loss": 0.4748,
|
| 61610 |
+
"step": 8800
|
| 61611 |
+
},
|
| 61612 |
+
{
|
| 61613 |
+
"epoch": 10.023931623931624,
|
| 61614 |
+
"grad_norm": 0.20948342978954315,
|
| 61615 |
+
"learning_rate": 2.6543536197513358e-05,
|
| 61616 |
+
"loss": 0.838,
|
| 61617 |
+
"step": 8801
|
| 61618 |
+
},
|
| 61619 |
+
{
|
| 61620 |
+
"epoch": 10.025071225071224,
|
| 61621 |
+
"grad_norm": 0.2177944779396057,
|
| 61622 |
+
"learning_rate": 2.6538885878496135e-05,
|
| 61623 |
+
"loss": 0.8068,
|
| 61624 |
+
"step": 8802
|
| 61625 |
+
},
|
| 61626 |
+
{
|
| 61627 |
+
"epoch": 10.026210826210827,
|
| 61628 |
+
"grad_norm": 0.2718174457550049,
|
| 61629 |
+
"learning_rate": 2.6534235506029165e-05,
|
| 61630 |
+
"loss": 0.5763,
|
| 61631 |
+
"step": 8803
|
| 61632 |
+
},
|
| 61633 |
+
{
|
| 61634 |
+
"epoch": 10.027350427350427,
|
| 61635 |
+
"grad_norm": 0.1805044412612915,
|
| 61636 |
+
"learning_rate": 2.6529585080273976e-05,
|
| 61637 |
+
"loss": 0.7984,
|
| 61638 |
+
"step": 8804
|
| 61639 |
+
},
|
| 61640 |
+
{
|
| 61641 |
+
"epoch": 10.028490028490028,
|
| 61642 |
+
"grad_norm": 0.22032229602336884,
|
| 61643 |
+
"learning_rate": 2.65249346013921e-05,
|
| 61644 |
+
"loss": 0.7791,
|
| 61645 |
+
"step": 8805
|
| 61646 |
+
},
|
| 61647 |
+
{
|
| 61648 |
+
"epoch": 10.02962962962963,
|
| 61649 |
+
"grad_norm": 0.19147786498069763,
|
| 61650 |
+
"learning_rate": 2.6520284069545044e-05,
|
| 61651 |
+
"loss": 0.6717,
|
| 61652 |
+
"step": 8806
|
| 61653 |
+
},
|
| 61654 |
+
{
|
| 61655 |
+
"epoch": 10.03076923076923,
|
| 61656 |
+
"grad_norm": 0.18560323119163513,
|
| 61657 |
+
"learning_rate": 2.6515633484894342e-05,
|
| 61658 |
+
"loss": 0.7543,
|
| 61659 |
+
"step": 8807
|
| 61660 |
+
},
|
| 61661 |
+
{
|
| 61662 |
+
"epoch": 10.031908831908831,
|
| 61663 |
+
"grad_norm": 0.1824505776166916,
|
| 61664 |
+
"learning_rate": 2.6510982847601525e-05,
|
| 61665 |
+
"loss": 0.7975,
|
| 61666 |
+
"step": 8808
|
| 61667 |
+
},
|
| 61668 |
+
{
|
| 61669 |
+
"epoch": 10.033048433048434,
|
| 61670 |
+
"grad_norm": 0.18685854971408844,
|
| 61671 |
+
"learning_rate": 2.6506332157828118e-05,
|
| 61672 |
+
"loss": 0.7852,
|
| 61673 |
+
"step": 8809
|
| 61674 |
+
},
|
| 61675 |
+
{
|
| 61676 |
+
"epoch": 10.034188034188034,
|
| 61677 |
+
"grad_norm": 0.17172589898109436,
|
| 61678 |
+
"learning_rate": 2.650168141573564e-05,
|
| 61679 |
+
"loss": 0.799,
|
| 61680 |
+
"step": 8810
|
| 61681 |
+
},
|
| 61682 |
+
{
|
| 61683 |
+
"epoch": 10.035327635327635,
|
| 61684 |
+
"grad_norm": 0.16937170922756195,
|
| 61685 |
+
"learning_rate": 2.6497030621485654e-05,
|
| 61686 |
+
"loss": 0.7407,
|
| 61687 |
+
"step": 8811
|
| 61688 |
+
},
|
| 61689 |
+
{
|
| 61690 |
+
"epoch": 10.036467236467237,
|
| 61691 |
+
"grad_norm": 0.24063147604465485,
|
| 61692 |
+
"learning_rate": 2.6492379775239668e-05,
|
| 61693 |
+
"loss": 0.5964,
|
| 61694 |
+
"step": 8812
|
| 61695 |
+
},
|
| 61696 |
+
{
|
| 61697 |
+
"epoch": 10.037606837606837,
|
| 61698 |
+
"grad_norm": 0.17484796047210693,
|
| 61699 |
+
"learning_rate": 2.6487728877159233e-05,
|
| 61700 |
+
"loss": 0.7741,
|
| 61701 |
+
"step": 8813
|
| 61702 |
+
},
|
| 61703 |
+
{
|
| 61704 |
+
"epoch": 10.038746438746438,
|
| 61705 |
+
"grad_norm": 0.17384153604507446,
|
| 61706 |
+
"learning_rate": 2.6483077927405882e-05,
|
| 61707 |
+
"loss": 0.8228,
|
| 61708 |
+
"step": 8814
|
| 61709 |
+
},
|
| 61710 |
+
{
|
| 61711 |
+
"epoch": 10.03988603988604,
|
| 61712 |
+
"grad_norm": 0.20385192334651947,
|
| 61713 |
+
"learning_rate": 2.6478426926141154e-05,
|
| 61714 |
+
"loss": 0.6191,
|
| 61715 |
+
"step": 8815
|
| 61716 |
+
},
|
| 61717 |
+
{
|
| 61718 |
+
"epoch": 10.04102564102564,
|
| 61719 |
+
"grad_norm": 0.18895360827445984,
|
| 61720 |
+
"learning_rate": 2.6473775873526595e-05,
|
| 61721 |
+
"loss": 0.6375,
|
| 61722 |
+
"step": 8816
|
| 61723 |
+
},
|
| 61724 |
+
{
|
| 61725 |
+
"epoch": 10.042165242165241,
|
| 61726 |
+
"grad_norm": 0.15249338746070862,
|
| 61727 |
+
"learning_rate": 2.6469124769723748e-05,
|
| 61728 |
+
"loss": 0.9603,
|
| 61729 |
+
"step": 8817
|
| 61730 |
+
},
|
| 61731 |
+
{
|
| 61732 |
+
"epoch": 10.043304843304844,
|
| 61733 |
+
"grad_norm": 0.24605506658554077,
|
| 61734 |
+
"learning_rate": 2.646447361489416e-05,
|
| 61735 |
+
"loss": 0.7325,
|
| 61736 |
+
"step": 8818
|
| 61737 |
+
},
|
| 61738 |
+
{
|
| 61739 |
+
"epoch": 10.044444444444444,
|
| 61740 |
+
"grad_norm": 0.17037871479988098,
|
| 61741 |
+
"learning_rate": 2.645982240919937e-05,
|
| 61742 |
+
"loss": 0.7791,
|
| 61743 |
+
"step": 8819
|
| 61744 |
+
},
|
| 61745 |
+
{
|
| 61746 |
+
"epoch": 10.045584045584045,
|
| 61747 |
+
"grad_norm": 0.19802500307559967,
|
| 61748 |
+
"learning_rate": 2.6455171152800933e-05,
|
| 61749 |
+
"loss": 0.6591,
|
| 61750 |
+
"step": 8820
|
| 61751 |
+
},
|
| 61752 |
+
{
|
| 61753 |
+
"epoch": 10.046723646723647,
|
| 61754 |
+
"grad_norm": 0.21303272247314453,
|
| 61755 |
+
"learning_rate": 2.64505198458604e-05,
|
| 61756 |
+
"loss": 0.5241,
|
| 61757 |
+
"step": 8821
|
| 61758 |
+
},
|
| 61759 |
+
{
|
| 61760 |
+
"epoch": 10.047863247863248,
|
| 61761 |
+
"grad_norm": 0.1992967426776886,
|
| 61762 |
+
"learning_rate": 2.6445868488539327e-05,
|
| 61763 |
+
"loss": 0.7214,
|
| 61764 |
+
"step": 8822
|
| 61765 |
+
},
|
| 61766 |
+
{
|
| 61767 |
+
"epoch": 10.049002849002848,
|
| 61768 |
+
"grad_norm": 0.22691546380519867,
|
| 61769 |
+
"learning_rate": 2.6441217080999264e-05,
|
| 61770 |
+
"loss": 0.7292,
|
| 61771 |
+
"step": 8823
|
| 61772 |
+
},
|
| 61773 |
+
{
|
| 61774 |
+
"epoch": 10.05014245014245,
|
| 61775 |
+
"grad_norm": 0.23367862403392792,
|
| 61776 |
+
"learning_rate": 2.643656562340177e-05,
|
| 61777 |
+
"loss": 0.5527,
|
| 61778 |
+
"step": 8824
|
| 61779 |
+
},
|
| 61780 |
+
{
|
| 61781 |
+
"epoch": 10.051282051282051,
|
| 61782 |
+
"grad_norm": 0.22327671945095062,
|
| 61783 |
+
"learning_rate": 2.64319141159084e-05,
|
| 61784 |
+
"loss": 0.4207,
|
| 61785 |
+
"step": 8825
|
| 61786 |
+
},
|
| 61787 |
+
{
|
| 61788 |
+
"epoch": 10.052421652421652,
|
| 61789 |
+
"grad_norm": 0.2017182856798172,
|
| 61790 |
+
"learning_rate": 2.642726255868071e-05,
|
| 61791 |
+
"loss": 0.588,
|
| 61792 |
+
"step": 8826
|
| 61793 |
+
},
|
| 61794 |
+
{
|
| 61795 |
+
"epoch": 10.053561253561254,
|
| 61796 |
+
"grad_norm": 0.18831363320350647,
|
| 61797 |
+
"learning_rate": 2.6422610951880272e-05,
|
| 61798 |
+
"loss": 0.7952,
|
| 61799 |
+
"step": 8827
|
| 61800 |
+
},
|
| 61801 |
+
{
|
| 61802 |
+
"epoch": 10.054700854700855,
|
| 61803 |
+
"grad_norm": 0.19915471971035004,
|
| 61804 |
+
"learning_rate": 2.641795929566865e-05,
|
| 61805 |
+
"loss": 0.6541,
|
| 61806 |
+
"step": 8828
|
| 61807 |
+
},
|
| 61808 |
+
{
|
| 61809 |
+
"epoch": 10.055840455840455,
|
| 61810 |
+
"grad_norm": 0.1804710179567337,
|
| 61811 |
+
"learning_rate": 2.6413307590207393e-05,
|
| 61812 |
+
"loss": 0.7298,
|
| 61813 |
+
"step": 8829
|
| 61814 |
+
},
|
| 61815 |
+
{
|
| 61816 |
+
"epoch": 10.056980056980057,
|
| 61817 |
+
"grad_norm": 0.20258505642414093,
|
| 61818 |
+
"learning_rate": 2.640865583565808e-05,
|
| 61819 |
+
"loss": 0.9078,
|
| 61820 |
+
"step": 8830
|
| 61821 |
+
},
|
| 61822 |
+
{
|
| 61823 |
+
"epoch": 10.058119658119658,
|
| 61824 |
+
"grad_norm": 0.20247726142406464,
|
| 61825 |
+
"learning_rate": 2.6404004032182272e-05,
|
| 61826 |
+
"loss": 0.6612,
|
| 61827 |
+
"step": 8831
|
| 61828 |
+
},
|
| 61829 |
+
{
|
| 61830 |
+
"epoch": 10.059259259259258,
|
| 61831 |
+
"grad_norm": 0.208050936460495,
|
| 61832 |
+
"learning_rate": 2.6399352179941543e-05,
|
| 61833 |
+
"loss": 0.6559,
|
| 61834 |
+
"step": 8832
|
| 61835 |
+
},
|
| 61836 |
+
{
|
| 61837 |
+
"epoch": 10.06039886039886,
|
| 61838 |
+
"grad_norm": 0.17111118137836456,
|
| 61839 |
+
"learning_rate": 2.639470027909747e-05,
|
| 61840 |
+
"loss": 0.7809,
|
| 61841 |
+
"step": 8833
|
| 61842 |
+
},
|
| 61843 |
+
{
|
| 61844 |
+
"epoch": 10.061538461538461,
|
| 61845 |
+
"grad_norm": 0.2093285322189331,
|
| 61846 |
+
"learning_rate": 2.639004832981162e-05,
|
| 61847 |
+
"loss": 0.5354,
|
| 61848 |
+
"step": 8834
|
| 61849 |
+
},
|
| 61850 |
+
{
|
| 61851 |
+
"epoch": 10.062678062678062,
|
| 61852 |
+
"grad_norm": 0.23502209782600403,
|
| 61853 |
+
"learning_rate": 2.6385396332245572e-05,
|
| 61854 |
+
"loss": 0.7269,
|
| 61855 |
+
"step": 8835
|
| 61856 |
+
},
|
| 61857 |
+
{
|
| 61858 |
+
"epoch": 10.063817663817664,
|
| 61859 |
+
"grad_norm": 0.20847783982753754,
|
| 61860 |
+
"learning_rate": 2.638074428656089e-05,
|
| 61861 |
+
"loss": 0.8058,
|
| 61862 |
+
"step": 8836
|
| 61863 |
+
},
|
| 61864 |
+
{
|
| 61865 |
+
"epoch": 10.064957264957265,
|
| 61866 |
+
"grad_norm": 0.2332785576581955,
|
| 61867 |
+
"learning_rate": 2.637609219291917e-05,
|
| 61868 |
+
"loss": 0.5732,
|
| 61869 |
+
"step": 8837
|
| 61870 |
+
},
|
| 61871 |
+
{
|
| 61872 |
+
"epoch": 10.066096866096865,
|
| 61873 |
+
"grad_norm": 0.22393395006656647,
|
| 61874 |
+
"learning_rate": 2.637144005148197e-05,
|
| 61875 |
+
"loss": 0.6826,
|
| 61876 |
+
"step": 8838
|
| 61877 |
+
},
|
| 61878 |
+
{
|
| 61879 |
+
"epoch": 10.067236467236468,
|
| 61880 |
+
"grad_norm": 0.25773870944976807,
|
| 61881 |
+
"learning_rate": 2.6366787862410902e-05,
|
| 61882 |
+
"loss": 0.6802,
|
| 61883 |
+
"step": 8839
|
| 61884 |
+
},
|
| 61885 |
+
{
|
| 61886 |
+
"epoch": 10.068376068376068,
|
| 61887 |
+
"grad_norm": 0.20467348396778107,
|
| 61888 |
+
"learning_rate": 2.6362135625867524e-05,
|
| 61889 |
+
"loss": 0.7429,
|
| 61890 |
+
"step": 8840
|
| 61891 |
+
},
|
| 61892 |
+
{
|
| 61893 |
+
"epoch": 10.069515669515669,
|
| 61894 |
+
"grad_norm": 0.23453713953495026,
|
| 61895 |
+
"learning_rate": 2.635748334201344e-05,
|
| 61896 |
+
"loss": 0.6959,
|
| 61897 |
+
"step": 8841
|
| 61898 |
+
},
|
| 61899 |
+
{
|
| 61900 |
+
"epoch": 10.070655270655271,
|
| 61901 |
+
"grad_norm": 0.18696318566799164,
|
| 61902 |
+
"learning_rate": 2.6352831011010216e-05,
|
| 61903 |
+
"loss": 0.7494,
|
| 61904 |
+
"step": 8842
|
| 61905 |
+
},
|
| 61906 |
+
{
|
| 61907 |
+
"epoch": 10.071794871794872,
|
| 61908 |
+
"grad_norm": 0.17967763543128967,
|
| 61909 |
+
"learning_rate": 2.634817863301945e-05,
|
| 61910 |
+
"loss": 0.7552,
|
| 61911 |
+
"step": 8843
|
| 61912 |
+
},
|
| 61913 |
+
{
|
| 61914 |
+
"epoch": 10.072934472934472,
|
| 61915 |
+
"grad_norm": 0.18998804688453674,
|
| 61916 |
+
"learning_rate": 2.6343526208202735e-05,
|
| 61917 |
+
"loss": 0.7303,
|
| 61918 |
+
"step": 8844
|
| 61919 |
+
},
|
| 61920 |
+
{
|
| 61921 |
+
"epoch": 10.074074074074074,
|
| 61922 |
+
"grad_norm": 0.22002533078193665,
|
| 61923 |
+
"learning_rate": 2.6338873736721664e-05,
|
| 61924 |
+
"loss": 0.4131,
|
| 61925 |
+
"step": 8845
|
| 61926 |
+
},
|
| 61927 |
+
{
|
| 61928 |
+
"epoch": 10.075213675213675,
|
| 61929 |
+
"grad_norm": 0.24679215252399445,
|
| 61930 |
+
"learning_rate": 2.6334221218737826e-05,
|
| 61931 |
+
"loss": 0.5834,
|
| 61932 |
+
"step": 8846
|
| 61933 |
+
},
|
| 61934 |
+
{
|
| 61935 |
+
"epoch": 10.076353276353275,
|
| 61936 |
+
"grad_norm": 0.24645689129829407,
|
| 61937 |
+
"learning_rate": 2.6329568654412812e-05,
|
| 61938 |
+
"loss": 0.561,
|
| 61939 |
+
"step": 8847
|
| 61940 |
+
},
|
| 61941 |
+
{
|
| 61942 |
+
"epoch": 10.077492877492878,
|
| 61943 |
+
"grad_norm": 0.19638419151306152,
|
| 61944 |
+
"learning_rate": 2.6324916043908226e-05,
|
| 61945 |
+
"loss": 0.6671,
|
| 61946 |
+
"step": 8848
|
| 61947 |
+
},
|
| 61948 |
+
{
|
| 61949 |
+
"epoch": 10.078632478632478,
|
| 61950 |
+
"grad_norm": 0.2307794988155365,
|
| 61951 |
+
"learning_rate": 2.6320263387385658e-05,
|
| 61952 |
+
"loss": 0.531,
|
| 61953 |
+
"step": 8849
|
| 61954 |
+
},
|
| 61955 |
+
{
|
| 61956 |
+
"epoch": 10.079772079772079,
|
| 61957 |
+
"grad_norm": 0.22745245695114136,
|
| 61958 |
+
"learning_rate": 2.6315610685006715e-05,
|
| 61959 |
+
"loss": 0.6205,
|
| 61960 |
+
"step": 8850
|
| 61961 |
+
},
|
| 61962 |
+
{
|
| 61963 |
+
"epoch": 10.080911680911681,
|
| 61964 |
+
"grad_norm": 0.1542021632194519,
|
| 61965 |
+
"learning_rate": 2.6310957936932994e-05,
|
| 61966 |
+
"loss": 0.7889,
|
| 61967 |
+
"step": 8851
|
| 61968 |
+
},
|
| 61969 |
+
{
|
| 61970 |
+
"epoch": 10.082051282051282,
|
| 61971 |
+
"grad_norm": 0.19776001572608948,
|
| 61972 |
+
"learning_rate": 2.63063051433261e-05,
|
| 61973 |
+
"loss": 0.7851,
|
| 61974 |
+
"step": 8852
|
| 61975 |
+
},
|
| 61976 |
+
{
|
| 61977 |
+
"epoch": 10.083190883190884,
|
| 61978 |
+
"grad_norm": 0.25708770751953125,
|
| 61979 |
+
"learning_rate": 2.6301652304347633e-05,
|
| 61980 |
+
"loss": 0.6544,
|
| 61981 |
+
"step": 8853
|
| 61982 |
+
},
|
| 61983 |
+
{
|
| 61984 |
+
"epoch": 10.084330484330485,
|
| 61985 |
+
"grad_norm": 0.19531428813934326,
|
| 61986 |
+
"learning_rate": 2.62969994201592e-05,
|
| 61987 |
+
"loss": 0.627,
|
| 61988 |
+
"step": 8854
|
| 61989 |
+
},
|
| 61990 |
+
{
|
| 61991 |
+
"epoch": 10.085470085470085,
|
| 61992 |
+
"grad_norm": 0.2588439881801605,
|
| 61993 |
+
"learning_rate": 2.6292346490922415e-05,
|
| 61994 |
+
"loss": 0.7755,
|
| 61995 |
+
"step": 8855
|
| 61996 |
+
},
|
| 61997 |
+
{
|
| 61998 |
+
"epoch": 10.086609686609687,
|
| 61999 |
+
"grad_norm": 0.17775475978851318,
|
| 62000 |
+
"learning_rate": 2.6287693516798884e-05,
|
| 62001 |
+
"loss": 0.8084,
|
| 62002 |
+
"step": 8856
|
| 62003 |
+
},
|
| 62004 |
+
{
|
| 62005 |
+
"epoch": 10.087749287749288,
|
| 62006 |
+
"grad_norm": 0.1992853581905365,
|
| 62007 |
+
"learning_rate": 2.628304049795021e-05,
|
| 62008 |
+
"loss": 0.9049,
|
| 62009 |
+
"step": 8857
|
| 62010 |
+
},
|
| 62011 |
+
{
|
| 62012 |
+
"epoch": 10.088888888888889,
|
| 62013 |
+
"grad_norm": 0.2174171358346939,
|
| 62014 |
+
"learning_rate": 2.6278387434538022e-05,
|
| 62015 |
+
"loss": 0.8111,
|
| 62016 |
+
"step": 8858
|
| 62017 |
+
},
|
| 62018 |
+
{
|
| 62019 |
+
"epoch": 10.090028490028491,
|
| 62020 |
+
"grad_norm": 0.23244938254356384,
|
| 62021 |
+
"learning_rate": 2.627373432672391e-05,
|
| 62022 |
+
"loss": 0.6628,
|
| 62023 |
+
"step": 8859
|
| 62024 |
+
},
|
| 62025 |
+
{
|
| 62026 |
+
"epoch": 10.091168091168091,
|
| 62027 |
+
"grad_norm": 0.21566203236579895,
|
| 62028 |
+
"learning_rate": 2.6269081174669507e-05,
|
| 62029 |
+
"loss": 0.5991,
|
| 62030 |
+
"step": 8860
|
| 62031 |
+
},
|
| 62032 |
+
{
|
| 62033 |
+
"epoch": 10.092307692307692,
|
| 62034 |
+
"grad_norm": 0.23708350956439972,
|
| 62035 |
+
"learning_rate": 2.626442797853642e-05,
|
| 62036 |
+
"loss": 0.8406,
|
| 62037 |
+
"step": 8861
|
| 62038 |
+
},
|
| 62039 |
+
{
|
| 62040 |
+
"epoch": 10.093447293447294,
|
| 62041 |
+
"grad_norm": 0.27565261721611023,
|
| 62042 |
+
"learning_rate": 2.6259774738486283e-05,
|
| 62043 |
+
"loss": 0.6404,
|
| 62044 |
+
"step": 8862
|
| 62045 |
+
},
|
| 62046 |
+
{
|
| 62047 |
+
"epoch": 10.094586894586895,
|
| 62048 |
+
"grad_norm": 0.23175352811813354,
|
| 62049 |
+
"learning_rate": 2.62551214546807e-05,
|
| 62050 |
+
"loss": 0.7613,
|
| 62051 |
+
"step": 8863
|
| 62052 |
+
},
|
| 62053 |
+
{
|
| 62054 |
+
"epoch": 10.095726495726495,
|
| 62055 |
+
"grad_norm": 0.20315219461917877,
|
| 62056 |
+
"learning_rate": 2.6250468127281298e-05,
|
| 62057 |
+
"loss": 0.7884,
|
| 62058 |
+
"step": 8864
|
| 62059 |
+
},
|
| 62060 |
+
{
|
| 62061 |
+
"epoch": 10.096866096866098,
|
| 62062 |
+
"grad_norm": 0.18797439336776733,
|
| 62063 |
+
"learning_rate": 2.6245814756449692e-05,
|
| 62064 |
+
"loss": 0.8777,
|
| 62065 |
+
"step": 8865
|
| 62066 |
+
},
|
| 62067 |
+
{
|
| 62068 |
+
"epoch": 10.098005698005698,
|
| 62069 |
+
"grad_norm": 0.21581979095935822,
|
| 62070 |
+
"learning_rate": 2.624116134234752e-05,
|
| 62071 |
+
"loss": 0.724,
|
| 62072 |
+
"step": 8866
|
| 62073 |
+
},
|
| 62074 |
+
{
|
| 62075 |
+
"epoch": 10.099145299145299,
|
| 62076 |
+
"grad_norm": 0.1983931064605713,
|
| 62077 |
+
"learning_rate": 2.6236507885136404e-05,
|
| 62078 |
+
"loss": 0.5552,
|
| 62079 |
+
"step": 8867
|
| 62080 |
+
},
|
| 62081 |
+
{
|
| 62082 |
+
"epoch": 10.100284900284901,
|
| 62083 |
+
"grad_norm": 0.214815154671669,
|
| 62084 |
+
"learning_rate": 2.6231854384977965e-05,
|
| 62085 |
+
"loss": 0.5143,
|
| 62086 |
+
"step": 8868
|
| 62087 |
+
},
|
| 62088 |
+
{
|
| 62089 |
+
"epoch": 10.101424501424502,
|
| 62090 |
+
"grad_norm": 0.19817157089710236,
|
| 62091 |
+
"learning_rate": 2.622720084203384e-05,
|
| 62092 |
+
"loss": 0.7363,
|
| 62093 |
+
"step": 8869
|
| 62094 |
+
},
|
| 62095 |
+
{
|
| 62096 |
+
"epoch": 10.102564102564102,
|
| 62097 |
+
"grad_norm": 0.20763924717903137,
|
| 62098 |
+
"learning_rate": 2.6222547256465646e-05,
|
| 62099 |
+
"loss": 0.5611,
|
| 62100 |
+
"step": 8870
|
| 62101 |
+
},
|
| 62102 |
+
{
|
| 62103 |
+
"epoch": 10.103703703703705,
|
| 62104 |
+
"grad_norm": 0.22716370224952698,
|
| 62105 |
+
"learning_rate": 2.621789362843503e-05,
|
| 62106 |
+
"loss": 0.6832,
|
| 62107 |
+
"step": 8871
|
| 62108 |
+
},
|
| 62109 |
+
{
|
| 62110 |
+
"epoch": 10.104843304843305,
|
| 62111 |
+
"grad_norm": 0.23576398193836212,
|
| 62112 |
+
"learning_rate": 2.6213239958103614e-05,
|
| 62113 |
+
"loss": 0.8271,
|
| 62114 |
+
"step": 8872
|
| 62115 |
+
},
|
| 62116 |
+
{
|
| 62117 |
+
"epoch": 10.105982905982906,
|
| 62118 |
+
"grad_norm": 0.23042328655719757,
|
| 62119 |
+
"learning_rate": 2.6208586245633043e-05,
|
| 62120 |
+
"loss": 0.728,
|
| 62121 |
+
"step": 8873
|
| 62122 |
+
},
|
| 62123 |
+
{
|
| 62124 |
+
"epoch": 10.107122507122508,
|
| 62125 |
+
"grad_norm": 0.17731733620166779,
|
| 62126 |
+
"learning_rate": 2.6203932491184946e-05,
|
| 62127 |
+
"loss": 0.7988,
|
| 62128 |
+
"step": 8874
|
| 62129 |
+
},
|
| 62130 |
+
{
|
| 62131 |
+
"epoch": 10.108262108262108,
|
| 62132 |
+
"grad_norm": 0.20725920796394348,
|
| 62133 |
+
"learning_rate": 2.6199278694920963e-05,
|
| 62134 |
+
"loss": 0.8181,
|
| 62135 |
+
"step": 8875
|
| 62136 |
+
},
|
| 62137 |
+
{
|
| 62138 |
+
"epoch": 10.109401709401709,
|
| 62139 |
+
"grad_norm": 0.16817273199558258,
|
| 62140 |
+
"learning_rate": 2.6194624857002736e-05,
|
| 62141 |
+
"loss": 0.767,
|
| 62142 |
+
"step": 8876
|
| 62143 |
+
},
|
| 62144 |
+
{
|
| 62145 |
+
"epoch": 10.110541310541311,
|
| 62146 |
+
"grad_norm": 0.25306424498558044,
|
| 62147 |
+
"learning_rate": 2.6189970977591898e-05,
|
| 62148 |
+
"loss": 0.5109,
|
| 62149 |
+
"step": 8877
|
| 62150 |
+
},
|
| 62151 |
+
{
|
| 62152 |
+
"epoch": 10.111680911680912,
|
| 62153 |
+
"grad_norm": 0.18125019967556,
|
| 62154 |
+
"learning_rate": 2.61853170568501e-05,
|
| 62155 |
+
"loss": 0.8867,
|
| 62156 |
+
"step": 8878
|
| 62157 |
+
},
|
| 62158 |
+
{
|
| 62159 |
+
"epoch": 10.112820512820512,
|
| 62160 |
+
"grad_norm": 0.21355712413787842,
|
| 62161 |
+
"learning_rate": 2.6180663094938973e-05,
|
| 62162 |
+
"loss": 0.769,
|
| 62163 |
+
"step": 8879
|
| 62164 |
+
},
|
| 62165 |
+
{
|
| 62166 |
+
"epoch": 10.113960113960115,
|
| 62167 |
+
"grad_norm": 0.1993047297000885,
|
| 62168 |
+
"learning_rate": 2.6176009092020175e-05,
|
| 62169 |
+
"loss": 0.7364,
|
| 62170 |
+
"step": 8880
|
| 62171 |
+
},
|
| 62172 |
+
{
|
| 62173 |
+
"epoch": 10.115099715099715,
|
| 62174 |
+
"grad_norm": 0.2002207636833191,
|
| 62175 |
+
"learning_rate": 2.6171355048255354e-05,
|
| 62176 |
+
"loss": 0.5944,
|
| 62177 |
+
"step": 8881
|
| 62178 |
+
},
|
| 62179 |
+
{
|
| 62180 |
+
"epoch": 10.116239316239316,
|
| 62181 |
+
"grad_norm": 0.20867647230625153,
|
| 62182 |
+
"learning_rate": 2.616670096380614e-05,
|
| 62183 |
+
"loss": 0.5918,
|
| 62184 |
+
"step": 8882
|
| 62185 |
+
},
|
| 62186 |
+
{
|
| 62187 |
+
"epoch": 10.117378917378918,
|
| 62188 |
+
"grad_norm": 0.21191585063934326,
|
| 62189 |
+
"learning_rate": 2.6162046838834197e-05,
|
| 62190 |
+
"loss": 0.5892,
|
| 62191 |
+
"step": 8883
|
| 62192 |
+
},
|
| 62193 |
+
{
|
| 62194 |
+
"epoch": 10.118518518518519,
|
| 62195 |
+
"grad_norm": 0.18844129145145416,
|
| 62196 |
+
"learning_rate": 2.6157392673501175e-05,
|
| 62197 |
+
"loss": 0.7598,
|
| 62198 |
+
"step": 8884
|
| 62199 |
+
},
|
| 62200 |
+
{
|
| 62201 |
+
"epoch": 10.11965811965812,
|
| 62202 |
+
"grad_norm": 0.1850503534078598,
|
| 62203 |
+
"learning_rate": 2.6152738467968717e-05,
|
| 62204 |
+
"loss": 0.7819,
|
| 62205 |
+
"step": 8885
|
| 62206 |
+
},
|
| 62207 |
+
{
|
| 62208 |
+
"epoch": 10.120797720797722,
|
| 62209 |
+
"grad_norm": 0.2429039627313614,
|
| 62210 |
+
"learning_rate": 2.614808422239849e-05,
|
| 62211 |
+
"loss": 0.5887,
|
| 62212 |
+
"step": 8886
|
| 62213 |
+
},
|
| 62214 |
+
{
|
| 62215 |
+
"epoch": 10.121937321937322,
|
| 62216 |
+
"grad_norm": 0.1783706396818161,
|
| 62217 |
+
"learning_rate": 2.6143429936952126e-05,
|
| 62218 |
+
"loss": 0.8119,
|
| 62219 |
+
"step": 8887
|
| 62220 |
+
},
|
| 62221 |
+
{
|
| 62222 |
+
"epoch": 10.123076923076923,
|
| 62223 |
+
"grad_norm": 0.21580688655376434,
|
| 62224 |
+
"learning_rate": 2.6138775611791304e-05,
|
| 62225 |
+
"loss": 0.6471,
|
| 62226 |
+
"step": 8888
|
| 62227 |
+
},
|
| 62228 |
+
{
|
| 62229 |
+
"epoch": 10.124216524216525,
|
| 62230 |
+
"grad_norm": 0.24312008917331696,
|
| 62231 |
+
"learning_rate": 2.6134121247077676e-05,
|
| 62232 |
+
"loss": 0.668,
|
| 62233 |
+
"step": 8889
|
| 62234 |
+
},
|
| 62235 |
+
{
|
| 62236 |
+
"epoch": 10.125356125356126,
|
| 62237 |
+
"grad_norm": 0.16163799166679382,
|
| 62238 |
+
"learning_rate": 2.61294668429729e-05,
|
| 62239 |
+
"loss": 0.8689,
|
| 62240 |
+
"step": 8890
|
| 62241 |
+
},
|
| 62242 |
+
{
|
| 62243 |
+
"epoch": 10.126495726495726,
|
| 62244 |
+
"grad_norm": 0.1943366676568985,
|
| 62245 |
+
"learning_rate": 2.6124812399638632e-05,
|
| 62246 |
+
"loss": 0.8453,
|
| 62247 |
+
"step": 8891
|
| 62248 |
+
},
|
| 62249 |
+
{
|
| 62250 |
+
"epoch": 10.127635327635328,
|
| 62251 |
+
"grad_norm": 0.21864405274391174,
|
| 62252 |
+
"learning_rate": 2.612015791723654e-05,
|
| 62253 |
+
"loss": 0.6204,
|
| 62254 |
+
"step": 8892
|
| 62255 |
+
},
|
| 62256 |
+
{
|
| 62257 |
+
"epoch": 10.128774928774929,
|
| 62258 |
+
"grad_norm": 0.22353316843509674,
|
| 62259 |
+
"learning_rate": 2.611550339592827e-05,
|
| 62260 |
+
"loss": 0.7569,
|
| 62261 |
+
"step": 8893
|
| 62262 |
+
},
|
| 62263 |
+
{
|
| 62264 |
+
"epoch": 10.12991452991453,
|
| 62265 |
+
"grad_norm": 0.21298466622829437,
|
| 62266 |
+
"learning_rate": 2.6110848835875506e-05,
|
| 62267 |
+
"loss": 0.7513,
|
| 62268 |
+
"step": 8894
|
| 62269 |
+
},
|
| 62270 |
+
{
|
| 62271 |
+
"epoch": 10.131054131054132,
|
| 62272 |
+
"grad_norm": 0.23452836275100708,
|
| 62273 |
+
"learning_rate": 2.6106194237239916e-05,
|
| 62274 |
+
"loss": 0.6682,
|
| 62275 |
+
"step": 8895
|
| 62276 |
+
},
|
| 62277 |
+
{
|
| 62278 |
+
"epoch": 10.132193732193732,
|
| 62279 |
+
"grad_norm": 0.30738216638565063,
|
| 62280 |
+
"learning_rate": 2.6101539600183146e-05,
|
| 62281 |
+
"loss": 0.3911,
|
| 62282 |
+
"step": 8896
|
| 62283 |
+
},
|
| 62284 |
+
{
|
| 62285 |
+
"epoch": 10.133333333333333,
|
| 62286 |
+
"grad_norm": 0.20332716405391693,
|
| 62287 |
+
"learning_rate": 2.6096884924866886e-05,
|
| 62288 |
+
"loss": 0.5929,
|
| 62289 |
+
"step": 8897
|
| 62290 |
+
},
|
| 62291 |
+
{
|
| 62292 |
+
"epoch": 10.134472934472935,
|
| 62293 |
+
"grad_norm": 0.17943629622459412,
|
| 62294 |
+
"learning_rate": 2.6092230211452783e-05,
|
| 62295 |
+
"loss": 0.7025,
|
| 62296 |
+
"step": 8898
|
| 62297 |
+
},
|
| 62298 |
+
{
|
| 62299 |
+
"epoch": 10.135612535612536,
|
| 62300 |
+
"grad_norm": 0.21828137338161469,
|
| 62301 |
+
"learning_rate": 2.6087575460102536e-05,
|
| 62302 |
+
"loss": 0.7702,
|
| 62303 |
+
"step": 8899
|
| 62304 |
+
},
|
| 62305 |
+
{
|
| 62306 |
+
"epoch": 10.136752136752136,
|
| 62307 |
+
"grad_norm": 0.1929798424243927,
|
| 62308 |
+
"learning_rate": 2.6082920670977795e-05,
|
| 62309 |
+
"loss": 0.6992,
|
| 62310 |
+
"step": 8900
|
| 62311 |
+
},
|
| 62312 |
+
{
|
| 62313 |
+
"epoch": 10.137891737891739,
|
| 62314 |
+
"grad_norm": 0.24545778334140778,
|
| 62315 |
+
"learning_rate": 2.6078265844240247e-05,
|
| 62316 |
+
"loss": 0.5378,
|
| 62317 |
+
"step": 8901
|
| 62318 |
+
},
|
| 62319 |
+
{
|
| 62320 |
+
"epoch": 10.13903133903134,
|
| 62321 |
+
"grad_norm": 0.27415305376052856,
|
| 62322 |
+
"learning_rate": 2.6073610980051548e-05,
|
| 62323 |
+
"loss": 0.4073,
|
| 62324 |
+
"step": 8902
|
| 62325 |
+
},
|
| 62326 |
+
{
|
| 62327 |
+
"epoch": 10.14017094017094,
|
| 62328 |
+
"grad_norm": 0.19098827242851257,
|
| 62329 |
+
"learning_rate": 2.6068956078573402e-05,
|
| 62330 |
+
"loss": 0.7139,
|
| 62331 |
+
"step": 8903
|
| 62332 |
+
},
|
| 62333 |
+
{
|
| 62334 |
+
"epoch": 10.141310541310542,
|
| 62335 |
+
"grad_norm": 0.1778879463672638,
|
| 62336 |
+
"learning_rate": 2.6064301139967458e-05,
|
| 62337 |
+
"loss": 0.8728,
|
| 62338 |
+
"step": 8904
|
| 62339 |
+
},
|
| 62340 |
+
{
|
| 62341 |
+
"epoch": 10.142450142450143,
|
| 62342 |
+
"grad_norm": 0.2150803506374359,
|
| 62343 |
+
"learning_rate": 2.6059646164395417e-05,
|
| 62344 |
+
"loss": 0.6732,
|
| 62345 |
+
"step": 8905
|
| 62346 |
+
},
|
| 62347 |
+
{
|
| 62348 |
+
"epoch": 10.143589743589743,
|
| 62349 |
+
"grad_norm": 0.24175742268562317,
|
| 62350 |
+
"learning_rate": 2.6054991152018947e-05,
|
| 62351 |
+
"loss": 0.6842,
|
| 62352 |
+
"step": 8906
|
| 62353 |
+
},
|
| 62354 |
+
{
|
| 62355 |
+
"epoch": 10.144729344729345,
|
| 62356 |
+
"grad_norm": 0.19339333474636078,
|
| 62357 |
+
"learning_rate": 2.605033610299974e-05,
|
| 62358 |
+
"loss": 0.7744,
|
| 62359 |
+
"step": 8907
|
| 62360 |
+
},
|
| 62361 |
+
{
|
| 62362 |
+
"epoch": 10.145868945868946,
|
| 62363 |
+
"grad_norm": 0.17048229277133942,
|
| 62364 |
+
"learning_rate": 2.6045681017499462e-05,
|
| 62365 |
+
"loss": 1.0048,
|
| 62366 |
+
"step": 8908
|
| 62367 |
+
},
|
| 62368 |
+
{
|
| 62369 |
+
"epoch": 10.147008547008546,
|
| 62370 |
+
"grad_norm": 0.21198265254497528,
|
| 62371 |
+
"learning_rate": 2.604102589567981e-05,
|
| 62372 |
+
"loss": 0.8113,
|
| 62373 |
+
"step": 8909
|
| 62374 |
+
},
|
| 62375 |
+
{
|
| 62376 |
+
"epoch": 10.148148148148149,
|
| 62377 |
+
"grad_norm": 0.234702005982399,
|
| 62378 |
+
"learning_rate": 2.6036370737702476e-05,
|
| 62379 |
+
"loss": 0.5801,
|
| 62380 |
+
"step": 8910
|
| 62381 |
+
},
|
| 62382 |
+
{
|
| 62383 |
+
"epoch": 10.14928774928775,
|
| 62384 |
+
"grad_norm": 0.22299301624298096,
|
| 62385 |
+
"learning_rate": 2.6031715543729125e-05,
|
| 62386 |
+
"loss": 0.6885,
|
| 62387 |
+
"step": 8911
|
| 62388 |
+
},
|
| 62389 |
+
{
|
| 62390 |
+
"epoch": 10.15042735042735,
|
| 62391 |
+
"grad_norm": 0.23150447010993958,
|
| 62392 |
+
"learning_rate": 2.602706031392146e-05,
|
| 62393 |
+
"loss": 0.6336,
|
| 62394 |
+
"step": 8912
|
| 62395 |
+
},
|
| 62396 |
+
{
|
| 62397 |
+
"epoch": 10.151566951566952,
|
| 62398 |
+
"grad_norm": 0.18681679666042328,
|
| 62399 |
+
"learning_rate": 2.602240504844116e-05,
|
| 62400 |
+
"loss": 0.8529,
|
| 62401 |
+
"step": 8913
|
| 62402 |
+
},
|
| 62403 |
+
{
|
| 62404 |
+
"epoch": 10.152706552706553,
|
| 62405 |
+
"grad_norm": 0.20661205053329468,
|
| 62406 |
+
"learning_rate": 2.601774974744993e-05,
|
| 62407 |
+
"loss": 0.6779,
|
| 62408 |
+
"step": 8914
|
| 62409 |
+
},
|
| 62410 |
+
{
|
| 62411 |
+
"epoch": 10.153846153846153,
|
| 62412 |
+
"grad_norm": 0.22453156113624573,
|
| 62413 |
+
"learning_rate": 2.6013094411109447e-05,
|
| 62414 |
+
"loss": 0.5817,
|
| 62415 |
+
"step": 8915
|
| 62416 |
+
},
|
| 62417 |
+
{
|
| 62418 |
+
"epoch": 10.154985754985756,
|
| 62419 |
+
"grad_norm": 0.20682759582996368,
|
| 62420 |
+
"learning_rate": 2.6008439039581412e-05,
|
| 62421 |
+
"loss": 0.5923,
|
| 62422 |
+
"step": 8916
|
| 62423 |
+
},
|
| 62424 |
+
{
|
| 62425 |
+
"epoch": 10.156125356125356,
|
| 62426 |
+
"grad_norm": 0.20472748577594757,
|
| 62427 |
+
"learning_rate": 2.6003783633027512e-05,
|
| 62428 |
+
"loss": 0.6358,
|
| 62429 |
+
"step": 8917
|
| 62430 |
+
},
|
| 62431 |
+
{
|
| 62432 |
+
"epoch": 10.157264957264957,
|
| 62433 |
+
"grad_norm": 0.21450816094875336,
|
| 62434 |
+
"learning_rate": 2.599912819160945e-05,
|
| 62435 |
+
"loss": 0.7361,
|
| 62436 |
+
"step": 8918
|
| 62437 |
+
},
|
| 62438 |
+
{
|
| 62439 |
+
"epoch": 10.158404558404559,
|
| 62440 |
+
"grad_norm": 0.2018934190273285,
|
| 62441 |
+
"learning_rate": 2.5994472715488917e-05,
|
| 62442 |
+
"loss": 0.6788,
|
| 62443 |
+
"step": 8919
|
| 62444 |
+
},
|
| 62445 |
+
{
|
| 62446 |
+
"epoch": 10.15954415954416,
|
| 62447 |
+
"grad_norm": 0.1991586983203888,
|
| 62448 |
+
"learning_rate": 2.5989817204827606e-05,
|
| 62449 |
+
"loss": 0.6879,
|
| 62450 |
+
"step": 8920
|
| 62451 |
+
},
|
| 62452 |
+
{
|
| 62453 |
+
"epoch": 10.16068376068376,
|
| 62454 |
+
"grad_norm": 0.22522181272506714,
|
| 62455 |
+
"learning_rate": 2.5985161659787227e-05,
|
| 62456 |
+
"loss": 0.5518,
|
| 62457 |
+
"step": 8921
|
| 62458 |
+
},
|
| 62459 |
+
{
|
| 62460 |
+
"epoch": 10.161823361823362,
|
| 62461 |
+
"grad_norm": 0.23106618225574493,
|
| 62462 |
+
"learning_rate": 2.5980506080529475e-05,
|
| 62463 |
+
"loss": 0.5903,
|
| 62464 |
+
"step": 8922
|
| 62465 |
+
},
|
| 62466 |
+
{
|
| 62467 |
+
"epoch": 10.162962962962963,
|
| 62468 |
+
"grad_norm": 0.24910876154899597,
|
| 62469 |
+
"learning_rate": 2.5975850467216045e-05,
|
| 62470 |
+
"loss": 0.5767,
|
| 62471 |
+
"step": 8923
|
| 62472 |
+
},
|
| 62473 |
+
{
|
| 62474 |
+
"epoch": 10.164102564102564,
|
| 62475 |
+
"grad_norm": 0.1799972653388977,
|
| 62476 |
+
"learning_rate": 2.5971194820008656e-05,
|
| 62477 |
+
"loss": 0.6332,
|
| 62478 |
+
"step": 8924
|
| 62479 |
+
},
|
| 62480 |
+
{
|
| 62481 |
+
"epoch": 10.165242165242166,
|
| 62482 |
+
"grad_norm": 0.21993529796600342,
|
| 62483 |
+
"learning_rate": 2.596653913906899e-05,
|
| 62484 |
+
"loss": 0.5968,
|
| 62485 |
+
"step": 8925
|
| 62486 |
+
},
|
| 62487 |
+
{
|
| 62488 |
+
"epoch": 10.166381766381766,
|
| 62489 |
+
"grad_norm": 0.19376817345619202,
|
| 62490 |
+
"learning_rate": 2.5961883424558764e-05,
|
| 62491 |
+
"loss": 0.6556,
|
| 62492 |
+
"step": 8926
|
| 62493 |
+
},
|
| 62494 |
+
{
|
| 62495 |
+
"epoch": 10.167521367521367,
|
| 62496 |
+
"grad_norm": 0.19510741531848907,
|
| 62497 |
+
"learning_rate": 2.5957227676639683e-05,
|
| 62498 |
+
"loss": 0.8258,
|
| 62499 |
+
"step": 8927
|
| 62500 |
+
},
|
| 62501 |
+
{
|
| 62502 |
+
"epoch": 10.16866096866097,
|
| 62503 |
+
"grad_norm": 0.2588106691837311,
|
| 62504 |
+
"learning_rate": 2.5952571895473454e-05,
|
| 62505 |
+
"loss": 0.7846,
|
| 62506 |
+
"step": 8928
|
| 62507 |
+
},
|
| 62508 |
+
{
|
| 62509 |
+
"epoch": 10.16980056980057,
|
| 62510 |
+
"grad_norm": 0.232466459274292,
|
| 62511 |
+
"learning_rate": 2.5947916081221786e-05,
|
| 62512 |
+
"loss": 0.5949,
|
| 62513 |
+
"step": 8929
|
| 62514 |
+
},
|
| 62515 |
+
{
|
| 62516 |
+
"epoch": 10.17094017094017,
|
| 62517 |
+
"grad_norm": 0.17070221900939941,
|
| 62518 |
+
"learning_rate": 2.5943260234046374e-05,
|
| 62519 |
+
"loss": 0.7432,
|
| 62520 |
+
"step": 8930
|
| 62521 |
+
},
|
| 62522 |
+
{
|
| 62523 |
+
"epoch": 10.172079772079773,
|
| 62524 |
+
"grad_norm": 0.2561127841472626,
|
| 62525 |
+
"learning_rate": 2.5938604354108948e-05,
|
| 62526 |
+
"loss": 0.4896,
|
| 62527 |
+
"step": 8931
|
| 62528 |
+
},
|
| 62529 |
+
{
|
| 62530 |
+
"epoch": 10.173219373219373,
|
| 62531 |
+
"grad_norm": 0.18016211688518524,
|
| 62532 |
+
"learning_rate": 2.593394844157121e-05,
|
| 62533 |
+
"loss": 0.7407,
|
| 62534 |
+
"step": 8932
|
| 62535 |
+
},
|
| 62536 |
+
{
|
| 62537 |
+
"epoch": 10.174358974358974,
|
| 62538 |
+
"grad_norm": 0.26223939657211304,
|
| 62539 |
+
"learning_rate": 2.5929292496594875e-05,
|
| 62540 |
+
"loss": 0.8116,
|
| 62541 |
+
"step": 8933
|
| 62542 |
+
},
|
| 62543 |
+
{
|
| 62544 |
+
"epoch": 10.175498575498576,
|
| 62545 |
+
"grad_norm": 0.2142946422100067,
|
| 62546 |
+
"learning_rate": 2.5924636519341654e-05,
|
| 62547 |
+
"loss": 0.7046,
|
| 62548 |
+
"step": 8934
|
| 62549 |
+
},
|
| 62550 |
+
{
|
| 62551 |
+
"epoch": 10.176638176638177,
|
| 62552 |
+
"grad_norm": 0.21094518899917603,
|
| 62553 |
+
"learning_rate": 2.591998050997327e-05,
|
| 62554 |
+
"loss": 0.5874,
|
| 62555 |
+
"step": 8935
|
| 62556 |
+
},
|
| 62557 |
+
{
|
| 62558 |
+
"epoch": 10.177777777777777,
|
| 62559 |
+
"grad_norm": 0.16477617621421814,
|
| 62560 |
+
"learning_rate": 2.5915324468651425e-05,
|
| 62561 |
+
"loss": 0.818,
|
| 62562 |
+
"step": 8936
|
| 62563 |
+
},
|
| 62564 |
+
{
|
| 62565 |
+
"epoch": 10.17891737891738,
|
| 62566 |
+
"grad_norm": 0.24145513772964478,
|
| 62567 |
+
"learning_rate": 2.5910668395537845e-05,
|
| 62568 |
+
"loss": 0.331,
|
| 62569 |
+
"step": 8937
|
| 62570 |
+
},
|
| 62571 |
+
{
|
| 62572 |
+
"epoch": 10.18005698005698,
|
| 62573 |
+
"grad_norm": 0.2187226116657257,
|
| 62574 |
+
"learning_rate": 2.5906012290794253e-05,
|
| 62575 |
+
"loss": 0.635,
|
| 62576 |
+
"step": 8938
|
| 62577 |
+
},
|
| 62578 |
+
{
|
| 62579 |
+
"epoch": 10.18119658119658,
|
| 62580 |
+
"grad_norm": 0.2143223136663437,
|
| 62581 |
+
"learning_rate": 2.5901356154582363e-05,
|
| 62582 |
+
"loss": 0.7668,
|
| 62583 |
+
"step": 8939
|
| 62584 |
+
},
|
| 62585 |
+
{
|
| 62586 |
+
"epoch": 10.182336182336183,
|
| 62587 |
+
"grad_norm": 0.2693440914154053,
|
| 62588 |
+
"learning_rate": 2.5896699987063888e-05,
|
| 62589 |
+
"loss": 0.4283,
|
| 62590 |
+
"step": 8940
|
| 62591 |
+
},
|
| 62592 |
+
{
|
| 62593 |
+
"epoch": 10.183475783475783,
|
| 62594 |
+
"grad_norm": 0.20912426710128784,
|
| 62595 |
+
"learning_rate": 2.5892043788400567e-05,
|
| 62596 |
+
"loss": 0.7052,
|
| 62597 |
+
"step": 8941
|
| 62598 |
+
},
|
| 62599 |
+
{
|
| 62600 |
+
"epoch": 10.184615384615384,
|
| 62601 |
+
"grad_norm": 0.15379904210567474,
|
| 62602 |
+
"learning_rate": 2.58873875587541e-05,
|
| 62603 |
+
"loss": 0.7951,
|
| 62604 |
+
"step": 8942
|
| 62605 |
+
},
|
| 62606 |
+
{
|
| 62607 |
+
"epoch": 10.185754985754986,
|
| 62608 |
+
"grad_norm": 0.21134737133979797,
|
| 62609 |
+
"learning_rate": 2.5882731298286227e-05,
|
| 62610 |
+
"loss": 0.7501,
|
| 62611 |
+
"step": 8943
|
| 62612 |
+
},
|
| 62613 |
+
{
|
| 62614 |
+
"epoch": 10.186894586894587,
|
| 62615 |
+
"grad_norm": 0.2301952987909317,
|
| 62616 |
+
"learning_rate": 2.587807500715867e-05,
|
| 62617 |
+
"loss": 0.6642,
|
| 62618 |
+
"step": 8944
|
| 62619 |
+
},
|
| 62620 |
+
{
|
| 62621 |
+
"epoch": 10.188034188034187,
|
| 62622 |
+
"grad_norm": 0.18264517188072205,
|
| 62623 |
+
"learning_rate": 2.587341868553315e-05,
|
| 62624 |
+
"loss": 0.8658,
|
| 62625 |
+
"step": 8945
|
| 62626 |
+
},
|
| 62627 |
+
{
|
| 62628 |
+
"epoch": 10.18917378917379,
|
| 62629 |
+
"grad_norm": 0.2299744039773941,
|
| 62630 |
+
"learning_rate": 2.5868762333571405e-05,
|
| 62631 |
+
"loss": 0.5489,
|
| 62632 |
+
"step": 8946
|
| 62633 |
+
},
|
| 62634 |
+
{
|
| 62635 |
+
"epoch": 10.19031339031339,
|
| 62636 |
+
"grad_norm": 0.15143314003944397,
|
| 62637 |
+
"learning_rate": 2.5864105951435147e-05,
|
| 62638 |
+
"loss": 0.9025,
|
| 62639 |
+
"step": 8947
|
| 62640 |
+
},
|
| 62641 |
+
{
|
| 62642 |
+
"epoch": 10.19145299145299,
|
| 62643 |
+
"grad_norm": 0.22624920308589935,
|
| 62644 |
+
"learning_rate": 2.5859449539286117e-05,
|
| 62645 |
+
"loss": 0.7747,
|
| 62646 |
+
"step": 8948
|
| 62647 |
+
},
|
| 62648 |
+
{
|
| 62649 |
+
"epoch": 10.192592592592593,
|
| 62650 |
+
"grad_norm": 0.1977541744709015,
|
| 62651 |
+
"learning_rate": 2.585479309728604e-05,
|
| 62652 |
+
"loss": 0.6921,
|
| 62653 |
+
"step": 8949
|
| 62654 |
+
},
|
| 62655 |
+
{
|
| 62656 |
+
"epoch": 10.193732193732194,
|
| 62657 |
+
"grad_norm": 0.21025383472442627,
|
| 62658 |
+
"learning_rate": 2.5850136625596648e-05,
|
| 62659 |
+
"loss": 0.6524,
|
| 62660 |
+
"step": 8950
|
| 62661 |
+
},
|
| 62662 |
+
{
|
| 62663 |
+
"epoch": 10.194871794871794,
|
| 62664 |
+
"grad_norm": 0.16774974763393402,
|
| 62665 |
+
"learning_rate": 2.5845480124379674e-05,
|
| 62666 |
+
"loss": 0.7247,
|
| 62667 |
+
"step": 8951
|
| 62668 |
+
},
|
| 62669 |
+
{
|
| 62670 |
+
"epoch": 10.196011396011396,
|
| 62671 |
+
"grad_norm": 0.15837088227272034,
|
| 62672 |
+
"learning_rate": 2.5840823593796853e-05,
|
| 62673 |
+
"loss": 0.7806,
|
| 62674 |
+
"step": 8952
|
| 62675 |
+
},
|
| 62676 |
+
{
|
| 62677 |
+
"epoch": 10.197150997150997,
|
| 62678 |
+
"grad_norm": 0.18233932554721832,
|
| 62679 |
+
"learning_rate": 2.5836167034009913e-05,
|
| 62680 |
+
"loss": 0.9084,
|
| 62681 |
+
"step": 8953
|
| 62682 |
+
},
|
| 62683 |
+
{
|
| 62684 |
+
"epoch": 10.198290598290598,
|
| 62685 |
+
"grad_norm": 0.18736779689788818,
|
| 62686 |
+
"learning_rate": 2.5831510445180584e-05,
|
| 62687 |
+
"loss": 0.71,
|
| 62688 |
+
"step": 8954
|
| 62689 |
+
},
|
| 62690 |
+
{
|
| 62691 |
+
"epoch": 10.1994301994302,
|
| 62692 |
+
"grad_norm": 0.2276691049337387,
|
| 62693 |
+
"learning_rate": 2.5826853827470626e-05,
|
| 62694 |
+
"loss": 0.7951,
|
| 62695 |
+
"step": 8955
|
| 62696 |
+
},
|
| 62697 |
+
{
|
| 62698 |
+
"epoch": 10.2005698005698,
|
| 62699 |
+
"grad_norm": 0.1869109719991684,
|
| 62700 |
+
"learning_rate": 2.5822197181041752e-05,
|
| 62701 |
+
"loss": 0.8659,
|
| 62702 |
+
"step": 8956
|
| 62703 |
+
},
|
| 62704 |
+
{
|
| 62705 |
+
"epoch": 10.201709401709401,
|
| 62706 |
+
"grad_norm": 0.17995122075080872,
|
| 62707 |
+
"learning_rate": 2.5817540506055715e-05,
|
| 62708 |
+
"loss": 0.7442,
|
| 62709 |
+
"step": 8957
|
| 62710 |
+
},
|
| 62711 |
+
{
|
| 62712 |
+
"epoch": 10.202849002849003,
|
| 62713 |
+
"grad_norm": 0.19730986654758453,
|
| 62714 |
+
"learning_rate": 2.5812883802674237e-05,
|
| 62715 |
+
"loss": 0.7441,
|
| 62716 |
+
"step": 8958
|
| 62717 |
+
},
|
| 62718 |
+
{
|
| 62719 |
+
"epoch": 10.203988603988604,
|
| 62720 |
+
"grad_norm": 0.1917230784893036,
|
| 62721 |
+
"learning_rate": 2.5808227071059076e-05,
|
| 62722 |
+
"loss": 0.8383,
|
| 62723 |
+
"step": 8959
|
| 62724 |
+
},
|
| 62725 |
+
{
|
| 62726 |
+
"epoch": 10.205128205128204,
|
| 62727 |
+
"grad_norm": 0.2498435229063034,
|
| 62728 |
+
"learning_rate": 2.580357031137196e-05,
|
| 62729 |
+
"loss": 0.719,
|
| 62730 |
+
"step": 8960
|
| 62731 |
+
},
|
| 62732 |
+
{
|
| 62733 |
+
"epoch": 10.206267806267807,
|
| 62734 |
+
"grad_norm": 0.26864364743232727,
|
| 62735 |
+
"learning_rate": 2.5798913523774648e-05,
|
| 62736 |
+
"loss": 0.5109,
|
| 62737 |
+
"step": 8961
|
| 62738 |
+
},
|
| 62739 |
+
{
|
| 62740 |
+
"epoch": 10.207407407407407,
|
| 62741 |
+
"grad_norm": 0.19821903109550476,
|
| 62742 |
+
"learning_rate": 2.5794256708428864e-05,
|
| 62743 |
+
"loss": 0.7657,
|
| 62744 |
+
"step": 8962
|
| 62745 |
+
},
|
| 62746 |
+
{
|
| 62747 |
+
"epoch": 10.208547008547008,
|
| 62748 |
+
"grad_norm": 0.21681812405586243,
|
| 62749 |
+
"learning_rate": 2.5789599865496373e-05,
|
| 62750 |
+
"loss": 0.7247,
|
| 62751 |
+
"step": 8963
|
| 62752 |
+
},
|
| 62753 |
+
{
|
| 62754 |
+
"epoch": 10.20968660968661,
|
| 62755 |
+
"grad_norm": 0.2496197521686554,
|
| 62756 |
+
"learning_rate": 2.5784942995138894e-05,
|
| 62757 |
+
"loss": 0.5004,
|
| 62758 |
+
"step": 8964
|
| 62759 |
+
},
|
| 62760 |
+
{
|
| 62761 |
+
"epoch": 10.21082621082621,
|
| 62762 |
+
"grad_norm": 0.20248307287693024,
|
| 62763 |
+
"learning_rate": 2.5780286097518184e-05,
|
| 62764 |
+
"loss": 0.7017,
|
| 62765 |
+
"step": 8965
|
| 62766 |
+
},
|
| 62767 |
+
{
|
| 62768 |
+
"epoch": 10.211965811965811,
|
| 62769 |
+
"grad_norm": 0.2095515877008438,
|
| 62770 |
+
"learning_rate": 2.5775629172795996e-05,
|
| 62771 |
+
"loss": 0.6386,
|
| 62772 |
+
"step": 8966
|
| 62773 |
+
},
|
| 62774 |
+
{
|
| 62775 |
+
"epoch": 10.213105413105414,
|
| 62776 |
+
"grad_norm": 0.231080561876297,
|
| 62777 |
+
"learning_rate": 2.5770972221134083e-05,
|
| 62778 |
+
"loss": 0.6178,
|
| 62779 |
+
"step": 8967
|
| 62780 |
+
},
|
| 62781 |
+
{
|
| 62782 |
+
"epoch": 10.214245014245014,
|
| 62783 |
+
"grad_norm": 0.20979668200016022,
|
| 62784 |
+
"learning_rate": 2.5766315242694172e-05,
|
| 62785 |
+
"loss": 0.6536,
|
| 62786 |
+
"step": 8968
|
| 62787 |
+
},
|
| 62788 |
+
{
|
| 62789 |
+
"epoch": 10.215384615384615,
|
| 62790 |
+
"grad_norm": 0.201679989695549,
|
| 62791 |
+
"learning_rate": 2.5761658237638037e-05,
|
| 62792 |
+
"loss": 0.6553,
|
| 62793 |
+
"step": 8969
|
| 62794 |
+
},
|
| 62795 |
+
{
|
| 62796 |
+
"epoch": 10.216524216524217,
|
| 62797 |
+
"grad_norm": 0.2316141426563263,
|
| 62798 |
+
"learning_rate": 2.5757001206127406e-05,
|
| 62799 |
+
"loss": 0.714,
|
| 62800 |
+
"step": 8970
|
| 62801 |
+
},
|
| 62802 |
+
{
|
| 62803 |
+
"epoch": 10.217663817663817,
|
| 62804 |
+
"grad_norm": 0.26693350076675415,
|
| 62805 |
+
"learning_rate": 2.5752344148324042e-05,
|
| 62806 |
+
"loss": 0.5044,
|
| 62807 |
+
"step": 8971
|
| 62808 |
+
},
|
| 62809 |
+
{
|
| 62810 |
+
"epoch": 10.218803418803418,
|
| 62811 |
+
"grad_norm": 0.2370952069759369,
|
| 62812 |
+
"learning_rate": 2.574768706438971e-05,
|
| 62813 |
+
"loss": 0.7485,
|
| 62814 |
+
"step": 8972
|
| 62815 |
+
},
|
| 62816 |
+
{
|
| 62817 |
+
"epoch": 10.21994301994302,
|
| 62818 |
+
"grad_norm": 0.23007620871067047,
|
| 62819 |
+
"learning_rate": 2.5743029954486137e-05,
|
| 62820 |
+
"loss": 0.7276,
|
| 62821 |
+
"step": 8973
|
| 62822 |
+
},
|
| 62823 |
+
{
|
| 62824 |
+
"epoch": 10.221082621082621,
|
| 62825 |
+
"grad_norm": 0.19329151511192322,
|
| 62826 |
+
"learning_rate": 2.57383728187751e-05,
|
| 62827 |
+
"loss": 0.643,
|
| 62828 |
+
"step": 8974
|
| 62829 |
+
},
|
| 62830 |
+
{
|
| 62831 |
+
"epoch": 10.222222222222221,
|
| 62832 |
+
"grad_norm": 0.1936943382024765,
|
| 62833 |
+
"learning_rate": 2.5733715657418332e-05,
|
| 62834 |
+
"loss": 0.7795,
|
| 62835 |
+
"step": 8975
|
| 62836 |
+
},
|
| 62837 |
+
{
|
| 62838 |
+
"epoch": 10.223361823361824,
|
| 62839 |
+
"grad_norm": 0.22971801459789276,
|
| 62840 |
+
"learning_rate": 2.5729058470577606e-05,
|
| 62841 |
+
"loss": 0.7746,
|
| 62842 |
+
"step": 8976
|
| 62843 |
+
},
|
| 62844 |
+
{
|
| 62845 |
+
"epoch": 10.224501424501424,
|
| 62846 |
+
"grad_norm": 0.18487688899040222,
|
| 62847 |
+
"learning_rate": 2.5724401258414675e-05,
|
| 62848 |
+
"loss": 0.8174,
|
| 62849 |
+
"step": 8977
|
| 62850 |
+
},
|
| 62851 |
+
{
|
| 62852 |
+
"epoch": 10.225641025641025,
|
| 62853 |
+
"grad_norm": 0.19056154787540436,
|
| 62854 |
+
"learning_rate": 2.57197440210913e-05,
|
| 62855 |
+
"loss": 0.7458,
|
| 62856 |
+
"step": 8978
|
| 62857 |
+
},
|
| 62858 |
+
{
|
| 62859 |
+
"epoch": 10.226780626780627,
|
| 62860 |
+
"grad_norm": 0.2256275713443756,
|
| 62861 |
+
"learning_rate": 2.571508675876923e-05,
|
| 62862 |
+
"loss": 0.8264,
|
| 62863 |
+
"step": 8979
|
| 62864 |
+
},
|
| 62865 |
+
{
|
| 62866 |
+
"epoch": 10.227920227920228,
|
| 62867 |
+
"grad_norm": 0.2609212398529053,
|
| 62868 |
+
"learning_rate": 2.5710429471610242e-05,
|
| 62869 |
+
"loss": 0.6448,
|
| 62870 |
+
"step": 8980
|
| 62871 |
+
},
|
| 62872 |
+
{
|
| 62873 |
+
"epoch": 10.229059829059828,
|
| 62874 |
+
"grad_norm": 0.2109462469816208,
|
| 62875 |
+
"learning_rate": 2.5705772159776066e-05,
|
| 62876 |
+
"loss": 0.6721,
|
| 62877 |
+
"step": 8981
|
| 62878 |
+
},
|
| 62879 |
+
{
|
| 62880 |
+
"epoch": 10.23019943019943,
|
| 62881 |
+
"grad_norm": 0.19234539568424225,
|
| 62882 |
+
"learning_rate": 2.5701114823428496e-05,
|
| 62883 |
+
"loss": 0.8113,
|
| 62884 |
+
"step": 8982
|
| 62885 |
+
},
|
| 62886 |
+
{
|
| 62887 |
+
"epoch": 10.231339031339031,
|
| 62888 |
+
"grad_norm": 0.21584919095039368,
|
| 62889 |
+
"learning_rate": 2.5696457462729274e-05,
|
| 62890 |
+
"loss": 0.6119,
|
| 62891 |
+
"step": 8983
|
| 62892 |
+
},
|
| 62893 |
+
{
|
| 62894 |
+
"epoch": 10.232478632478632,
|
| 62895 |
+
"grad_norm": 0.2534079849720001,
|
| 62896 |
+
"learning_rate": 2.5691800077840177e-05,
|
| 62897 |
+
"loss": 0.6815,
|
| 62898 |
+
"step": 8984
|
| 62899 |
+
},
|
| 62900 |
+
{
|
| 62901 |
+
"epoch": 10.233618233618234,
|
| 62902 |
+
"grad_norm": 0.23516786098480225,
|
| 62903 |
+
"learning_rate": 2.5687142668922954e-05,
|
| 62904 |
+
"loss": 0.6465,
|
| 62905 |
+
"step": 8985
|
| 62906 |
+
},
|
| 62907 |
+
{
|
| 62908 |
+
"epoch": 10.234757834757835,
|
| 62909 |
+
"grad_norm": 0.19675037264823914,
|
| 62910 |
+
"learning_rate": 2.568248523613938e-05,
|
| 62911 |
+
"loss": 0.8126,
|
| 62912 |
+
"step": 8986
|
| 62913 |
+
},
|
| 62914 |
+
{
|
| 62915 |
+
"epoch": 10.235897435897435,
|
| 62916 |
+
"grad_norm": 0.19146771728992462,
|
| 62917 |
+
"learning_rate": 2.5677827779651216e-05,
|
| 62918 |
+
"loss": 0.636,
|
| 62919 |
+
"step": 8987
|
| 62920 |
+
},
|
| 62921 |
+
{
|
| 62922 |
+
"epoch": 10.237037037037037,
|
| 62923 |
+
"grad_norm": 0.20973047614097595,
|
| 62924 |
+
"learning_rate": 2.5673170299620224e-05,
|
| 62925 |
+
"loss": 0.7118,
|
| 62926 |
+
"step": 8988
|
| 62927 |
+
},
|
| 62928 |
+
{
|
| 62929 |
+
"epoch": 10.238176638176638,
|
| 62930 |
+
"grad_norm": 0.20711617171764374,
|
| 62931 |
+
"learning_rate": 2.566851279620818e-05,
|
| 62932 |
+
"loss": 0.6087,
|
| 62933 |
+
"step": 8989
|
| 62934 |
+
},
|
| 62935 |
+
{
|
| 62936 |
+
"epoch": 10.239316239316238,
|
| 62937 |
+
"grad_norm": 0.21229654550552368,
|
| 62938 |
+
"learning_rate": 2.5663855269576852e-05,
|
| 62939 |
+
"loss": 0.5955,
|
| 62940 |
+
"step": 8990
|
| 62941 |
+
},
|
| 62942 |
+
{
|
| 62943 |
+
"epoch": 10.24045584045584,
|
| 62944 |
+
"grad_norm": 0.2514808177947998,
|
| 62945 |
+
"learning_rate": 2.5659197719888005e-05,
|
| 62946 |
+
"loss": 0.5145,
|
| 62947 |
+
"step": 8991
|
| 62948 |
+
},
|
| 62949 |
+
{
|
| 62950 |
+
"epoch": 10.241595441595441,
|
| 62951 |
+
"grad_norm": 0.2512102723121643,
|
| 62952 |
+
"learning_rate": 2.5654540147303396e-05,
|
| 62953 |
+
"loss": 0.5224,
|
| 62954 |
+
"step": 8992
|
| 62955 |
+
},
|
| 62956 |
+
{
|
| 62957 |
+
"epoch": 10.242735042735042,
|
| 62958 |
+
"grad_norm": 0.2813994884490967,
|
| 62959 |
+
"learning_rate": 2.5649882551984823e-05,
|
| 62960 |
+
"loss": 0.6023,
|
| 62961 |
+
"step": 8993
|
| 62962 |
+
},
|
| 62963 |
+
{
|
| 62964 |
+
"epoch": 10.243874643874644,
|
| 62965 |
+
"grad_norm": 0.2017429769039154,
|
| 62966 |
+
"learning_rate": 2.564522493409403e-05,
|
| 62967 |
+
"loss": 0.5882,
|
| 62968 |
+
"step": 8994
|
| 62969 |
+
},
|
| 62970 |
+
{
|
| 62971 |
+
"epoch": 10.245014245014245,
|
| 62972 |
+
"grad_norm": 0.18968677520751953,
|
| 62973 |
+
"learning_rate": 2.564056729379281e-05,
|
| 62974 |
+
"loss": 0.8654,
|
| 62975 |
+
"step": 8995
|
| 62976 |
+
},
|
| 62977 |
+
{
|
| 62978 |
+
"epoch": 10.246153846153845,
|
| 62979 |
+
"grad_norm": 0.20515674352645874,
|
| 62980 |
+
"learning_rate": 2.5635909631242923e-05,
|
| 62981 |
+
"loss": 0.7102,
|
| 62982 |
+
"step": 8996
|
| 62983 |
+
},
|
| 62984 |
+
{
|
| 62985 |
+
"epoch": 10.247293447293448,
|
| 62986 |
+
"grad_norm": 0.20291048288345337,
|
| 62987 |
+
"learning_rate": 2.5631251946606145e-05,
|
| 62988 |
+
"loss": 0.7177,
|
| 62989 |
+
"step": 8997
|
| 62990 |
+
},
|
| 62991 |
+
{
|
| 62992 |
+
"epoch": 10.248433048433048,
|
| 62993 |
+
"grad_norm": 0.19213135540485382,
|
| 62994 |
+
"learning_rate": 2.5626594240044245e-05,
|
| 62995 |
+
"loss": 0.6859,
|
| 62996 |
+
"step": 8998
|
| 62997 |
+
},
|
| 62998 |
+
{
|
| 62999 |
+
"epoch": 10.249572649572649,
|
| 63000 |
+
"grad_norm": 0.20880888402462006,
|
| 63001 |
+
"learning_rate": 2.5621936511719015e-05,
|
| 63002 |
+
"loss": 0.7952,
|
| 63003 |
+
"step": 8999
|
| 63004 |
+
},
|
| 63005 |
+
{
|
| 63006 |
+
"epoch": 10.250712250712251,
|
| 63007 |
+
"grad_norm": 0.198693186044693,
|
| 63008 |
+
"learning_rate": 2.5617278761792206e-05,
|
| 63009 |
+
"loss": 0.5229,
|
| 63010 |
+
"step": 9000
|
| 63011 |
}
|
| 63012 |
],
|
| 63013 |
"logging_steps": 1,
|
|
|
|
| 63027 |
"attributes": {}
|
| 63028 |
}
|
| 63029 |
},
|
| 63030 |
+
"total_flos": 5.032145044173423e+19,
|
| 63031 |
"train_batch_size": 8,
|
| 63032 |
"trial_name": null,
|
| 63033 |
"trial_params": null
|