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 4500, 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:a867ce14a8485d11abfa1dc51cf0e3dc12f213688e789a97d2b492d7b85a3679
|
| 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 sha256:0f1d6db269461ecd0127d85f7b6a1073d83f0cb17c344dff22213794cfbd1eb6
|
| 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 sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
|
| 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:c4323ba8f20e24ce6c7407c940004f59a37a6c3b7847865a78d09b0b35e6a84d
|
| 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,
|
|
@@ -29408,6 +29408,2106 @@
|
|
| 29408 |
"learning_rate": 4.487877337194388e-05,
|
| 29409 |
"loss": 0.7887,
|
| 29410 |
"step": 4200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29411 |
}
|
| 29412 |
],
|
| 29413 |
"logging_steps": 1,
|
|
@@ -29427,7 +31527,7 @@
|
|
| 29427 |
"attributes": {}
|
| 29428 |
}
|
| 29429 |
},
|
| 29430 |
-
"total_flos": 2.
|
| 29431 |
"train_batch_size": 8,
|
| 29432 |
"trial_name": null,
|
| 29433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.1253561253561255,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 29408 |
"learning_rate": 4.487877337194388e-05,
|
| 29409 |
"loss": 0.7887,
|
| 29410 |
"step": 4200
|
| 29411 |
+
},
|
| 29412 |
+
{
|
| 29413 |
+
"epoch": 4.785185185185185,
|
| 29414 |
+
"grad_norm": 0.14604023098945618,
|
| 29415 |
+
"learning_rate": 4.4875947645398554e-05,
|
| 29416 |
+
"loss": 0.8949,
|
| 29417 |
+
"step": 4201
|
| 29418 |
+
},
|
| 29419 |
+
{
|
| 29420 |
+
"epoch": 4.786324786324786,
|
| 29421 |
+
"grad_norm": 0.15411163866519928,
|
| 29422 |
+
"learning_rate": 4.48731212285069e-05,
|
| 29423 |
+
"loss": 0.8067,
|
| 29424 |
+
"step": 4202
|
| 29425 |
+
},
|
| 29426 |
+
{
|
| 29427 |
+
"epoch": 4.787464387464388,
|
| 29428 |
+
"grad_norm": 0.18294286727905273,
|
| 29429 |
+
"learning_rate": 4.48702941213671e-05,
|
| 29430 |
+
"loss": 0.6416,
|
| 29431 |
+
"step": 4203
|
| 29432 |
+
},
|
| 29433 |
+
{
|
| 29434 |
+
"epoch": 4.788603988603988,
|
| 29435 |
+
"grad_norm": 0.17204371094703674,
|
| 29436 |
+
"learning_rate": 4.4867466324077344e-05,
|
| 29437 |
+
"loss": 0.7774,
|
| 29438 |
+
"step": 4204
|
| 29439 |
+
},
|
| 29440 |
+
{
|
| 29441 |
+
"epoch": 4.78974358974359,
|
| 29442 |
+
"grad_norm": 0.14938533306121826,
|
| 29443 |
+
"learning_rate": 4.4864637836735844e-05,
|
| 29444 |
+
"loss": 0.7033,
|
| 29445 |
+
"step": 4205
|
| 29446 |
+
},
|
| 29447 |
+
{
|
| 29448 |
+
"epoch": 4.790883190883191,
|
| 29449 |
+
"grad_norm": 0.14529328048229218,
|
| 29450 |
+
"learning_rate": 4.486180865944084e-05,
|
| 29451 |
+
"loss": 0.8266,
|
| 29452 |
+
"step": 4206
|
| 29453 |
+
},
|
| 29454 |
+
{
|
| 29455 |
+
"epoch": 4.792022792022792,
|
| 29456 |
+
"grad_norm": 0.1788632571697235,
|
| 29457 |
+
"learning_rate": 4.485897879229061e-05,
|
| 29458 |
+
"loss": 0.7094,
|
| 29459 |
+
"step": 4207
|
| 29460 |
+
},
|
| 29461 |
+
{
|
| 29462 |
+
"epoch": 4.793162393162393,
|
| 29463 |
+
"grad_norm": 0.16603273153305054,
|
| 29464 |
+
"learning_rate": 4.485614823538343e-05,
|
| 29465 |
+
"loss": 0.7224,
|
| 29466 |
+
"step": 4208
|
| 29467 |
+
},
|
| 29468 |
+
{
|
| 29469 |
+
"epoch": 4.794301994301994,
|
| 29470 |
+
"grad_norm": 0.18029817938804626,
|
| 29471 |
+
"learning_rate": 4.485331698881762e-05,
|
| 29472 |
+
"loss": 0.8077,
|
| 29473 |
+
"step": 4209
|
| 29474 |
+
},
|
| 29475 |
+
{
|
| 29476 |
+
"epoch": 4.795441595441595,
|
| 29477 |
+
"grad_norm": 0.1685163378715515,
|
| 29478 |
+
"learning_rate": 4.4850485052691507e-05,
|
| 29479 |
+
"loss": 0.8523,
|
| 29480 |
+
"step": 4210
|
| 29481 |
+
},
|
| 29482 |
+
{
|
| 29483 |
+
"epoch": 4.796581196581196,
|
| 29484 |
+
"grad_norm": 0.17367805540561676,
|
| 29485 |
+
"learning_rate": 4.4847652427103465e-05,
|
| 29486 |
+
"loss": 0.7716,
|
| 29487 |
+
"step": 4211
|
| 29488 |
+
},
|
| 29489 |
+
{
|
| 29490 |
+
"epoch": 4.797720797720798,
|
| 29491 |
+
"grad_norm": 0.1601673662662506,
|
| 29492 |
+
"learning_rate": 4.484481911215187e-05,
|
| 29493 |
+
"loss": 0.747,
|
| 29494 |
+
"step": 4212
|
| 29495 |
+
},
|
| 29496 |
+
{
|
| 29497 |
+
"epoch": 4.798860398860398,
|
| 29498 |
+
"grad_norm": 0.13713626563549042,
|
| 29499 |
+
"learning_rate": 4.484198510793514e-05,
|
| 29500 |
+
"loss": 0.9217,
|
| 29501 |
+
"step": 4213
|
| 29502 |
+
},
|
| 29503 |
+
{
|
| 29504 |
+
"epoch": 4.8,
|
| 29505 |
+
"grad_norm": 0.17279836535453796,
|
| 29506 |
+
"learning_rate": 4.4839150414551686e-05,
|
| 29507 |
+
"loss": 0.7968,
|
| 29508 |
+
"step": 4214
|
| 29509 |
+
},
|
| 29510 |
+
{
|
| 29511 |
+
"epoch": 4.801139601139601,
|
| 29512 |
+
"grad_norm": 0.19132784008979797,
|
| 29513 |
+
"learning_rate": 4.48363150321e-05,
|
| 29514 |
+
"loss": 0.7535,
|
| 29515 |
+
"step": 4215
|
| 29516 |
+
},
|
| 29517 |
+
{
|
| 29518 |
+
"epoch": 4.802279202279202,
|
| 29519 |
+
"grad_norm": 0.16383789479732513,
|
| 29520 |
+
"learning_rate": 4.4833478960678535e-05,
|
| 29521 |
+
"loss": 0.6406,
|
| 29522 |
+
"step": 4216
|
| 29523 |
+
},
|
| 29524 |
+
{
|
| 29525 |
+
"epoch": 4.803418803418803,
|
| 29526 |
+
"grad_norm": 0.18167129158973694,
|
| 29527 |
+
"learning_rate": 4.4830642200385795e-05,
|
| 29528 |
+
"loss": 0.8526,
|
| 29529 |
+
"step": 4217
|
| 29530 |
+
},
|
| 29531 |
+
{
|
| 29532 |
+
"epoch": 4.804558404558405,
|
| 29533 |
+
"grad_norm": 0.1492447853088379,
|
| 29534 |
+
"learning_rate": 4.482780475132032e-05,
|
| 29535 |
+
"loss": 0.78,
|
| 29536 |
+
"step": 4218
|
| 29537 |
+
},
|
| 29538 |
+
{
|
| 29539 |
+
"epoch": 4.805698005698005,
|
| 29540 |
+
"grad_norm": 0.15305733680725098,
|
| 29541 |
+
"learning_rate": 4.4824966613580664e-05,
|
| 29542 |
+
"loss": 0.7064,
|
| 29543 |
+
"step": 4219
|
| 29544 |
+
},
|
| 29545 |
+
{
|
| 29546 |
+
"epoch": 4.806837606837607,
|
| 29547 |
+
"grad_norm": 0.1457163393497467,
|
| 29548 |
+
"learning_rate": 4.48221277872654e-05,
|
| 29549 |
+
"loss": 0.8307,
|
| 29550 |
+
"step": 4220
|
| 29551 |
+
},
|
| 29552 |
+
{
|
| 29553 |
+
"epoch": 4.807977207977208,
|
| 29554 |
+
"grad_norm": 0.1764405071735382,
|
| 29555 |
+
"learning_rate": 4.4819288272473125e-05,
|
| 29556 |
+
"loss": 0.8535,
|
| 29557 |
+
"step": 4221
|
| 29558 |
+
},
|
| 29559 |
+
{
|
| 29560 |
+
"epoch": 4.8091168091168095,
|
| 29561 |
+
"grad_norm": 0.1517675220966339,
|
| 29562 |
+
"learning_rate": 4.481644806930247e-05,
|
| 29563 |
+
"loss": 0.7826,
|
| 29564 |
+
"step": 4222
|
| 29565 |
+
},
|
| 29566 |
+
{
|
| 29567 |
+
"epoch": 4.81025641025641,
|
| 29568 |
+
"grad_norm": 0.15232150256633759,
|
| 29569 |
+
"learning_rate": 4.481360717785207e-05,
|
| 29570 |
+
"loss": 0.8085,
|
| 29571 |
+
"step": 4223
|
| 29572 |
+
},
|
| 29573 |
+
{
|
| 29574 |
+
"epoch": 4.8113960113960115,
|
| 29575 |
+
"grad_norm": 0.1400236189365387,
|
| 29576 |
+
"learning_rate": 4.48107655982206e-05,
|
| 29577 |
+
"loss": 0.9212,
|
| 29578 |
+
"step": 4224
|
| 29579 |
+
},
|
| 29580 |
+
{
|
| 29581 |
+
"epoch": 4.812535612535613,
|
| 29582 |
+
"grad_norm": 0.197129487991333,
|
| 29583 |
+
"learning_rate": 4.480792333050678e-05,
|
| 29584 |
+
"loss": 0.6547,
|
| 29585 |
+
"step": 4225
|
| 29586 |
+
},
|
| 29587 |
+
{
|
| 29588 |
+
"epoch": 4.8136752136752134,
|
| 29589 |
+
"grad_norm": 0.15185502171516418,
|
| 29590 |
+
"learning_rate": 4.48050803748093e-05,
|
| 29591 |
+
"loss": 0.8662,
|
| 29592 |
+
"step": 4226
|
| 29593 |
+
},
|
| 29594 |
+
{
|
| 29595 |
+
"epoch": 4.814814814814815,
|
| 29596 |
+
"grad_norm": 0.18135321140289307,
|
| 29597 |
+
"learning_rate": 4.480223673122691e-05,
|
| 29598 |
+
"loss": 0.7618,
|
| 29599 |
+
"step": 4227
|
| 29600 |
+
},
|
| 29601 |
+
{
|
| 29602 |
+
"epoch": 4.815954415954416,
|
| 29603 |
+
"grad_norm": 0.14626853168010712,
|
| 29604 |
+
"learning_rate": 4.4799392399858384e-05,
|
| 29605 |
+
"loss": 0.9952,
|
| 29606 |
+
"step": 4228
|
| 29607 |
+
},
|
| 29608 |
+
{
|
| 29609 |
+
"epoch": 4.817094017094017,
|
| 29610 |
+
"grad_norm": 0.1954558938741684,
|
| 29611 |
+
"learning_rate": 4.479654738080252e-05,
|
| 29612 |
+
"loss": 0.6954,
|
| 29613 |
+
"step": 4229
|
| 29614 |
+
},
|
| 29615 |
+
{
|
| 29616 |
+
"epoch": 4.818233618233618,
|
| 29617 |
+
"grad_norm": 0.17472834885120392,
|
| 29618 |
+
"learning_rate": 4.479370167415812e-05,
|
| 29619 |
+
"loss": 0.6557,
|
| 29620 |
+
"step": 4230
|
| 29621 |
+
},
|
| 29622 |
+
{
|
| 29623 |
+
"epoch": 4.81937321937322,
|
| 29624 |
+
"grad_norm": 0.17346905171871185,
|
| 29625 |
+
"learning_rate": 4.4790855280024026e-05,
|
| 29626 |
+
"loss": 0.7406,
|
| 29627 |
+
"step": 4231
|
| 29628 |
+
},
|
| 29629 |
+
{
|
| 29630 |
+
"epoch": 4.82051282051282,
|
| 29631 |
+
"grad_norm": 0.1571098119020462,
|
| 29632 |
+
"learning_rate": 4.4788008198499095e-05,
|
| 29633 |
+
"loss": 0.8376,
|
| 29634 |
+
"step": 4232
|
| 29635 |
+
},
|
| 29636 |
+
{
|
| 29637 |
+
"epoch": 4.821652421652422,
|
| 29638 |
+
"grad_norm": 0.16063807904720306,
|
| 29639 |
+
"learning_rate": 4.478516042968224e-05,
|
| 29640 |
+
"loss": 0.7809,
|
| 29641 |
+
"step": 4233
|
| 29642 |
+
},
|
| 29643 |
+
{
|
| 29644 |
+
"epoch": 4.822792022792023,
|
| 29645 |
+
"grad_norm": 0.19099533557891846,
|
| 29646 |
+
"learning_rate": 4.4782311973672345e-05,
|
| 29647 |
+
"loss": 0.7096,
|
| 29648 |
+
"step": 4234
|
| 29649 |
+
},
|
| 29650 |
+
{
|
| 29651 |
+
"epoch": 4.823931623931624,
|
| 29652 |
+
"grad_norm": 0.19397708773612976,
|
| 29653 |
+
"learning_rate": 4.4779462830568344e-05,
|
| 29654 |
+
"loss": 0.6659,
|
| 29655 |
+
"step": 4235
|
| 29656 |
+
},
|
| 29657 |
+
{
|
| 29658 |
+
"epoch": 4.825071225071225,
|
| 29659 |
+
"grad_norm": 0.23969055712223053,
|
| 29660 |
+
"learning_rate": 4.477661300046921e-05,
|
| 29661 |
+
"loss": 0.7448,
|
| 29662 |
+
"step": 4236
|
| 29663 |
+
},
|
| 29664 |
+
{
|
| 29665 |
+
"epoch": 4.8262108262108265,
|
| 29666 |
+
"grad_norm": 0.20346936583518982,
|
| 29667 |
+
"learning_rate": 4.477376248347393e-05,
|
| 29668 |
+
"loss": 0.783,
|
| 29669 |
+
"step": 4237
|
| 29670 |
+
},
|
| 29671 |
+
{
|
| 29672 |
+
"epoch": 4.827350427350427,
|
| 29673 |
+
"grad_norm": 0.15883132815361023,
|
| 29674 |
+
"learning_rate": 4.4770911279681496e-05,
|
| 29675 |
+
"loss": 0.9055,
|
| 29676 |
+
"step": 4238
|
| 29677 |
+
},
|
| 29678 |
+
{
|
| 29679 |
+
"epoch": 4.8284900284900285,
|
| 29680 |
+
"grad_norm": 0.1544889211654663,
|
| 29681 |
+
"learning_rate": 4.476805938919094e-05,
|
| 29682 |
+
"loss": 0.8677,
|
| 29683 |
+
"step": 4239
|
| 29684 |
+
},
|
| 29685 |
+
{
|
| 29686 |
+
"epoch": 4.82962962962963,
|
| 29687 |
+
"grad_norm": 0.16251614689826965,
|
| 29688 |
+
"learning_rate": 4.476520681210132e-05,
|
| 29689 |
+
"loss": 0.8046,
|
| 29690 |
+
"step": 4240
|
| 29691 |
+
},
|
| 29692 |
+
{
|
| 29693 |
+
"epoch": 4.8307692307692305,
|
| 29694 |
+
"grad_norm": 0.15391865372657776,
|
| 29695 |
+
"learning_rate": 4.476235354851172e-05,
|
| 29696 |
+
"loss": 0.7789,
|
| 29697 |
+
"step": 4241
|
| 29698 |
+
},
|
| 29699 |
+
{
|
| 29700 |
+
"epoch": 4.831908831908832,
|
| 29701 |
+
"grad_norm": 0.1404588669538498,
|
| 29702 |
+
"learning_rate": 4.475949959852123e-05,
|
| 29703 |
+
"loss": 0.8876,
|
| 29704 |
+
"step": 4242
|
| 29705 |
+
},
|
| 29706 |
+
{
|
| 29707 |
+
"epoch": 4.833048433048433,
|
| 29708 |
+
"grad_norm": 0.17338310182094574,
|
| 29709 |
+
"learning_rate": 4.475664496222898e-05,
|
| 29710 |
+
"loss": 0.8681,
|
| 29711 |
+
"step": 4243
|
| 29712 |
+
},
|
| 29713 |
+
{
|
| 29714 |
+
"epoch": 4.834188034188034,
|
| 29715 |
+
"grad_norm": 0.15925438702106476,
|
| 29716 |
+
"learning_rate": 4.475378963973411e-05,
|
| 29717 |
+
"loss": 0.7407,
|
| 29718 |
+
"step": 4244
|
| 29719 |
+
},
|
| 29720 |
+
{
|
| 29721 |
+
"epoch": 4.835327635327635,
|
| 29722 |
+
"grad_norm": 0.15909427404403687,
|
| 29723 |
+
"learning_rate": 4.475093363113582e-05,
|
| 29724 |
+
"loss": 0.912,
|
| 29725 |
+
"step": 4245
|
| 29726 |
+
},
|
| 29727 |
+
{
|
| 29728 |
+
"epoch": 4.836467236467237,
|
| 29729 |
+
"grad_norm": 0.16174373030662537,
|
| 29730 |
+
"learning_rate": 4.474807693653328e-05,
|
| 29731 |
+
"loss": 0.7123,
|
| 29732 |
+
"step": 4246
|
| 29733 |
+
},
|
| 29734 |
+
{
|
| 29735 |
+
"epoch": 4.837606837606837,
|
| 29736 |
+
"grad_norm": 0.1355389803647995,
|
| 29737 |
+
"learning_rate": 4.474521955602572e-05,
|
| 29738 |
+
"loss": 1.0165,
|
| 29739 |
+
"step": 4247
|
| 29740 |
+
},
|
| 29741 |
+
{
|
| 29742 |
+
"epoch": 4.838746438746439,
|
| 29743 |
+
"grad_norm": 0.16957055032253265,
|
| 29744 |
+
"learning_rate": 4.4742361489712383e-05,
|
| 29745 |
+
"loss": 0.8319,
|
| 29746 |
+
"step": 4248
|
| 29747 |
+
},
|
| 29748 |
+
{
|
| 29749 |
+
"epoch": 4.83988603988604,
|
| 29750 |
+
"grad_norm": 0.1739952564239502,
|
| 29751 |
+
"learning_rate": 4.473950273769255e-05,
|
| 29752 |
+
"loss": 0.8228,
|
| 29753 |
+
"step": 4249
|
| 29754 |
+
},
|
| 29755 |
+
{
|
| 29756 |
+
"epoch": 4.841025641025641,
|
| 29757 |
+
"grad_norm": 0.15971599519252777,
|
| 29758 |
+
"learning_rate": 4.473664330006549e-05,
|
| 29759 |
+
"loss": 0.7937,
|
| 29760 |
+
"step": 4250
|
| 29761 |
+
},
|
| 29762 |
+
{
|
| 29763 |
+
"epoch": 4.842165242165242,
|
| 29764 |
+
"grad_norm": 0.1937943696975708,
|
| 29765 |
+
"learning_rate": 4.473378317693054e-05,
|
| 29766 |
+
"loss": 0.7698,
|
| 29767 |
+
"step": 4251
|
| 29768 |
+
},
|
| 29769 |
+
{
|
| 29770 |
+
"epoch": 4.843304843304844,
|
| 29771 |
+
"grad_norm": 0.19935311377048492,
|
| 29772 |
+
"learning_rate": 4.473092236838703e-05,
|
| 29773 |
+
"loss": 0.6701,
|
| 29774 |
+
"step": 4252
|
| 29775 |
+
},
|
| 29776 |
+
{
|
| 29777 |
+
"epoch": 4.844444444444444,
|
| 29778 |
+
"grad_norm": 0.15304085612297058,
|
| 29779 |
+
"learning_rate": 4.4728060874534325e-05,
|
| 29780 |
+
"loss": 0.6718,
|
| 29781 |
+
"step": 4253
|
| 29782 |
+
},
|
| 29783 |
+
{
|
| 29784 |
+
"epoch": 4.8455840455840455,
|
| 29785 |
+
"grad_norm": 0.17695607244968414,
|
| 29786 |
+
"learning_rate": 4.472519869547182e-05,
|
| 29787 |
+
"loss": 0.7867,
|
| 29788 |
+
"step": 4254
|
| 29789 |
+
},
|
| 29790 |
+
{
|
| 29791 |
+
"epoch": 4.846723646723647,
|
| 29792 |
+
"grad_norm": 0.15410280227661133,
|
| 29793 |
+
"learning_rate": 4.472233583129891e-05,
|
| 29794 |
+
"loss": 0.8369,
|
| 29795 |
+
"step": 4255
|
| 29796 |
+
},
|
| 29797 |
+
{
|
| 29798 |
+
"epoch": 4.8478632478632475,
|
| 29799 |
+
"grad_norm": 0.4089936912059784,
|
| 29800 |
+
"learning_rate": 4.471947228211505e-05,
|
| 29801 |
+
"loss": 0.6676,
|
| 29802 |
+
"step": 4256
|
| 29803 |
+
},
|
| 29804 |
+
{
|
| 29805 |
+
"epoch": 4.849002849002849,
|
| 29806 |
+
"grad_norm": 0.18327905237674713,
|
| 29807 |
+
"learning_rate": 4.471660804801968e-05,
|
| 29808 |
+
"loss": 0.7837,
|
| 29809 |
+
"step": 4257
|
| 29810 |
+
},
|
| 29811 |
+
{
|
| 29812 |
+
"epoch": 4.85014245014245,
|
| 29813 |
+
"grad_norm": 0.16768579185009003,
|
| 29814 |
+
"learning_rate": 4.47137431291123e-05,
|
| 29815 |
+
"loss": 0.8029,
|
| 29816 |
+
"step": 4258
|
| 29817 |
+
},
|
| 29818 |
+
{
|
| 29819 |
+
"epoch": 4.851282051282051,
|
| 29820 |
+
"grad_norm": 0.15602938830852509,
|
| 29821 |
+
"learning_rate": 4.47108775254924e-05,
|
| 29822 |
+
"loss": 0.9681,
|
| 29823 |
+
"step": 4259
|
| 29824 |
+
},
|
| 29825 |
+
{
|
| 29826 |
+
"epoch": 4.852421652421652,
|
| 29827 |
+
"grad_norm": 0.17325910925865173,
|
| 29828 |
+
"learning_rate": 4.470801123725953e-05,
|
| 29829 |
+
"loss": 0.8651,
|
| 29830 |
+
"step": 4260
|
| 29831 |
+
},
|
| 29832 |
+
{
|
| 29833 |
+
"epoch": 4.853561253561254,
|
| 29834 |
+
"grad_norm": 0.15763314068317413,
|
| 29835 |
+
"learning_rate": 4.4705144264513224e-05,
|
| 29836 |
+
"loss": 0.8297,
|
| 29837 |
+
"step": 4261
|
| 29838 |
+
},
|
| 29839 |
+
{
|
| 29840 |
+
"epoch": 4.854700854700854,
|
| 29841 |
+
"grad_norm": 0.14961732923984528,
|
| 29842 |
+
"learning_rate": 4.4702276607353064e-05,
|
| 29843 |
+
"loss": 0.9468,
|
| 29844 |
+
"step": 4262
|
| 29845 |
+
},
|
| 29846 |
+
{
|
| 29847 |
+
"epoch": 4.855840455840456,
|
| 29848 |
+
"grad_norm": 0.15746955573558807,
|
| 29849 |
+
"learning_rate": 4.4699408265878665e-05,
|
| 29850 |
+
"loss": 0.7486,
|
| 29851 |
+
"step": 4263
|
| 29852 |
+
},
|
| 29853 |
+
{
|
| 29854 |
+
"epoch": 4.856980056980057,
|
| 29855 |
+
"grad_norm": 0.1406732201576233,
|
| 29856 |
+
"learning_rate": 4.469653924018964e-05,
|
| 29857 |
+
"loss": 1.0252,
|
| 29858 |
+
"step": 4264
|
| 29859 |
+
},
|
| 29860 |
+
{
|
| 29861 |
+
"epoch": 4.858119658119658,
|
| 29862 |
+
"grad_norm": 0.1895042359828949,
|
| 29863 |
+
"learning_rate": 4.469366953038564e-05,
|
| 29864 |
+
"loss": 0.6633,
|
| 29865 |
+
"step": 4265
|
| 29866 |
+
},
|
| 29867 |
+
{
|
| 29868 |
+
"epoch": 4.859259259259259,
|
| 29869 |
+
"grad_norm": 0.1835954189300537,
|
| 29870 |
+
"learning_rate": 4.4690799136566336e-05,
|
| 29871 |
+
"loss": 0.6703,
|
| 29872 |
+
"step": 4266
|
| 29873 |
+
},
|
| 29874 |
+
{
|
| 29875 |
+
"epoch": 4.860398860398861,
|
| 29876 |
+
"grad_norm": 0.16680637001991272,
|
| 29877 |
+
"learning_rate": 4.468792805883143e-05,
|
| 29878 |
+
"loss": 0.8152,
|
| 29879 |
+
"step": 4267
|
| 29880 |
+
},
|
| 29881 |
+
{
|
| 29882 |
+
"epoch": 4.861538461538462,
|
| 29883 |
+
"grad_norm": 0.1416798233985901,
|
| 29884 |
+
"learning_rate": 4.468505629728065e-05,
|
| 29885 |
+
"loss": 1.0173,
|
| 29886 |
+
"step": 4268
|
| 29887 |
+
},
|
| 29888 |
+
{
|
| 29889 |
+
"epoch": 4.862678062678063,
|
| 29890 |
+
"grad_norm": 0.1459040343761444,
|
| 29891 |
+
"learning_rate": 4.468218385201372e-05,
|
| 29892 |
+
"loss": 0.8913,
|
| 29893 |
+
"step": 4269
|
| 29894 |
+
},
|
| 29895 |
+
{
|
| 29896 |
+
"epoch": 4.863817663817664,
|
| 29897 |
+
"grad_norm": 0.1507241427898407,
|
| 29898 |
+
"learning_rate": 4.4679310723130416e-05,
|
| 29899 |
+
"loss": 0.7986,
|
| 29900 |
+
"step": 4270
|
| 29901 |
+
},
|
| 29902 |
+
{
|
| 29903 |
+
"epoch": 4.864957264957265,
|
| 29904 |
+
"grad_norm": 0.17497318983078003,
|
| 29905 |
+
"learning_rate": 4.4676436910730546e-05,
|
| 29906 |
+
"loss": 0.8781,
|
| 29907 |
+
"step": 4271
|
| 29908 |
+
},
|
| 29909 |
+
{
|
| 29910 |
+
"epoch": 4.866096866096866,
|
| 29911 |
+
"grad_norm": 0.1836574673652649,
|
| 29912 |
+
"learning_rate": 4.467356241491391e-05,
|
| 29913 |
+
"loss": 0.6725,
|
| 29914 |
+
"step": 4272
|
| 29915 |
+
},
|
| 29916 |
+
{
|
| 29917 |
+
"epoch": 4.867236467236467,
|
| 29918 |
+
"grad_norm": 0.13472136855125427,
|
| 29919 |
+
"learning_rate": 4.467068723578033e-05,
|
| 29920 |
+
"loss": 0.906,
|
| 29921 |
+
"step": 4273
|
| 29922 |
+
},
|
| 29923 |
+
{
|
| 29924 |
+
"epoch": 4.868376068376069,
|
| 29925 |
+
"grad_norm": 0.14699387550354004,
|
| 29926 |
+
"learning_rate": 4.4667811373429704e-05,
|
| 29927 |
+
"loss": 0.8387,
|
| 29928 |
+
"step": 4274
|
| 29929 |
+
},
|
| 29930 |
+
{
|
| 29931 |
+
"epoch": 4.869515669515669,
|
| 29932 |
+
"grad_norm": 0.1765470951795578,
|
| 29933 |
+
"learning_rate": 4.4664934827961905e-05,
|
| 29934 |
+
"loss": 0.8405,
|
| 29935 |
+
"step": 4275
|
| 29936 |
+
},
|
| 29937 |
+
{
|
| 29938 |
+
"epoch": 4.870655270655271,
|
| 29939 |
+
"grad_norm": 0.15825481712818146,
|
| 29940 |
+
"learning_rate": 4.466205759947683e-05,
|
| 29941 |
+
"loss": 0.8911,
|
| 29942 |
+
"step": 4276
|
| 29943 |
+
},
|
| 29944 |
+
{
|
| 29945 |
+
"epoch": 4.871794871794872,
|
| 29946 |
+
"grad_norm": 0.14879028499126434,
|
| 29947 |
+
"learning_rate": 4.4659179688074425e-05,
|
| 29948 |
+
"loss": 0.9072,
|
| 29949 |
+
"step": 4277
|
| 29950 |
+
},
|
| 29951 |
+
{
|
| 29952 |
+
"epoch": 4.872934472934473,
|
| 29953 |
+
"grad_norm": 0.16699357330799103,
|
| 29954 |
+
"learning_rate": 4.465630109385465e-05,
|
| 29955 |
+
"loss": 0.7287,
|
| 29956 |
+
"step": 4278
|
| 29957 |
+
},
|
| 29958 |
+
{
|
| 29959 |
+
"epoch": 4.874074074074074,
|
| 29960 |
+
"grad_norm": 0.1636863797903061,
|
| 29961 |
+
"learning_rate": 4.465342181691748e-05,
|
| 29962 |
+
"loss": 0.8981,
|
| 29963 |
+
"step": 4279
|
| 29964 |
+
},
|
| 29965 |
+
{
|
| 29966 |
+
"epoch": 4.875213675213676,
|
| 29967 |
+
"grad_norm": 0.1806856244802475,
|
| 29968 |
+
"learning_rate": 4.465054185736293e-05,
|
| 29969 |
+
"loss": 0.727,
|
| 29970 |
+
"step": 4280
|
| 29971 |
+
},
|
| 29972 |
+
{
|
| 29973 |
+
"epoch": 4.876353276353276,
|
| 29974 |
+
"grad_norm": 0.1562328040599823,
|
| 29975 |
+
"learning_rate": 4.464766121529102e-05,
|
| 29976 |
+
"loss": 0.7446,
|
| 29977 |
+
"step": 4281
|
| 29978 |
+
},
|
| 29979 |
+
{
|
| 29980 |
+
"epoch": 4.877492877492878,
|
| 29981 |
+
"grad_norm": 0.18651501834392548,
|
| 29982 |
+
"learning_rate": 4.46447798908018e-05,
|
| 29983 |
+
"loss": 0.7936,
|
| 29984 |
+
"step": 4282
|
| 29985 |
+
},
|
| 29986 |
+
{
|
| 29987 |
+
"epoch": 4.878632478632479,
|
| 29988 |
+
"grad_norm": 0.14649750292301178,
|
| 29989 |
+
"learning_rate": 4.464189788399535e-05,
|
| 29990 |
+
"loss": 0.7607,
|
| 29991 |
+
"step": 4283
|
| 29992 |
+
},
|
| 29993 |
+
{
|
| 29994 |
+
"epoch": 4.87977207977208,
|
| 29995 |
+
"grad_norm": 0.16038383543491364,
|
| 29996 |
+
"learning_rate": 4.463901519497178e-05,
|
| 29997 |
+
"loss": 0.9292,
|
| 29998 |
+
"step": 4284
|
| 29999 |
+
},
|
| 30000 |
+
{
|
| 30001 |
+
"epoch": 4.880911680911681,
|
| 30002 |
+
"grad_norm": 0.18320301175117493,
|
| 30003 |
+
"learning_rate": 4.463613182383119e-05,
|
| 30004 |
+
"loss": 0.6915,
|
| 30005 |
+
"step": 4285
|
| 30006 |
+
},
|
| 30007 |
+
{
|
| 30008 |
+
"epoch": 4.8820512820512825,
|
| 30009 |
+
"grad_norm": 0.15676233172416687,
|
| 30010 |
+
"learning_rate": 4.463324777067376e-05,
|
| 30011 |
+
"loss": 0.8755,
|
| 30012 |
+
"step": 4286
|
| 30013 |
+
},
|
| 30014 |
+
{
|
| 30015 |
+
"epoch": 4.883190883190883,
|
| 30016 |
+
"grad_norm": 0.1492704153060913,
|
| 30017 |
+
"learning_rate": 4.463036303559964e-05,
|
| 30018 |
+
"loss": 0.7828,
|
| 30019 |
+
"step": 4287
|
| 30020 |
+
},
|
| 30021 |
+
{
|
| 30022 |
+
"epoch": 4.8843304843304844,
|
| 30023 |
+
"grad_norm": 0.18921218812465668,
|
| 30024 |
+
"learning_rate": 4.462747761870902e-05,
|
| 30025 |
+
"loss": 0.6043,
|
| 30026 |
+
"step": 4288
|
| 30027 |
+
},
|
| 30028 |
+
{
|
| 30029 |
+
"epoch": 4.885470085470086,
|
| 30030 |
+
"grad_norm": 0.15510891377925873,
|
| 30031 |
+
"learning_rate": 4.4624591520102124e-05,
|
| 30032 |
+
"loss": 0.9145,
|
| 30033 |
+
"step": 4289
|
| 30034 |
+
},
|
| 30035 |
+
{
|
| 30036 |
+
"epoch": 4.886609686609686,
|
| 30037 |
+
"grad_norm": 0.14122672379016876,
|
| 30038 |
+
"learning_rate": 4.4621704739879204e-05,
|
| 30039 |
+
"loss": 0.757,
|
| 30040 |
+
"step": 4290
|
| 30041 |
+
},
|
| 30042 |
+
{
|
| 30043 |
+
"epoch": 4.887749287749288,
|
| 30044 |
+
"grad_norm": 0.17758646607398987,
|
| 30045 |
+
"learning_rate": 4.461881727814052e-05,
|
| 30046 |
+
"loss": 0.7638,
|
| 30047 |
+
"step": 4291
|
| 30048 |
+
},
|
| 30049 |
+
{
|
| 30050 |
+
"epoch": 4.888888888888889,
|
| 30051 |
+
"grad_norm": 0.16042566299438477,
|
| 30052 |
+
"learning_rate": 4.4615929134986356e-05,
|
| 30053 |
+
"loss": 0.8693,
|
| 30054 |
+
"step": 4292
|
| 30055 |
+
},
|
| 30056 |
+
{
|
| 30057 |
+
"epoch": 4.89002849002849,
|
| 30058 |
+
"grad_norm": 0.17387689650058746,
|
| 30059 |
+
"learning_rate": 4.461304031051703e-05,
|
| 30060 |
+
"loss": 0.8141,
|
| 30061 |
+
"step": 4293
|
| 30062 |
+
},
|
| 30063 |
+
{
|
| 30064 |
+
"epoch": 4.891168091168091,
|
| 30065 |
+
"grad_norm": 0.15727101266384125,
|
| 30066 |
+
"learning_rate": 4.461015080483287e-05,
|
| 30067 |
+
"loss": 0.8782,
|
| 30068 |
+
"step": 4294
|
| 30069 |
+
},
|
| 30070 |
+
{
|
| 30071 |
+
"epoch": 4.892307692307693,
|
| 30072 |
+
"grad_norm": 0.17457790672779083,
|
| 30073 |
+
"learning_rate": 4.4607260618034256e-05,
|
| 30074 |
+
"loss": 0.6134,
|
| 30075 |
+
"step": 4295
|
| 30076 |
+
},
|
| 30077 |
+
{
|
| 30078 |
+
"epoch": 4.893447293447293,
|
| 30079 |
+
"grad_norm": 0.15576937794685364,
|
| 30080 |
+
"learning_rate": 4.460436975022156e-05,
|
| 30081 |
+
"loss": 0.7734,
|
| 30082 |
+
"step": 4296
|
| 30083 |
+
},
|
| 30084 |
+
{
|
| 30085 |
+
"epoch": 4.894586894586895,
|
| 30086 |
+
"grad_norm": 0.17607951164245605,
|
| 30087 |
+
"learning_rate": 4.460147820149518e-05,
|
| 30088 |
+
"loss": 0.822,
|
| 30089 |
+
"step": 4297
|
| 30090 |
+
},
|
| 30091 |
+
{
|
| 30092 |
+
"epoch": 4.895726495726496,
|
| 30093 |
+
"grad_norm": 0.17070811986923218,
|
| 30094 |
+
"learning_rate": 4.459858597195557e-05,
|
| 30095 |
+
"loss": 0.802,
|
| 30096 |
+
"step": 4298
|
| 30097 |
+
},
|
| 30098 |
+
{
|
| 30099 |
+
"epoch": 4.896866096866097,
|
| 30100 |
+
"grad_norm": 0.18165738880634308,
|
| 30101 |
+
"learning_rate": 4.459569306170317e-05,
|
| 30102 |
+
"loss": 0.6937,
|
| 30103 |
+
"step": 4299
|
| 30104 |
+
},
|
| 30105 |
+
{
|
| 30106 |
+
"epoch": 4.898005698005698,
|
| 30107 |
+
"grad_norm": 0.18264617025852203,
|
| 30108 |
+
"learning_rate": 4.459279947083846e-05,
|
| 30109 |
+
"loss": 0.7236,
|
| 30110 |
+
"step": 4300
|
| 30111 |
+
},
|
| 30112 |
+
{
|
| 30113 |
+
"epoch": 4.8991452991452995,
|
| 30114 |
+
"grad_norm": 0.15589116513729095,
|
| 30115 |
+
"learning_rate": 4.4589905199461946e-05,
|
| 30116 |
+
"loss": 0.9915,
|
| 30117 |
+
"step": 4301
|
| 30118 |
+
},
|
| 30119 |
+
{
|
| 30120 |
+
"epoch": 4.9002849002849,
|
| 30121 |
+
"grad_norm": 0.1613919734954834,
|
| 30122 |
+
"learning_rate": 4.458701024767414e-05,
|
| 30123 |
+
"loss": 0.7948,
|
| 30124 |
+
"step": 4302
|
| 30125 |
+
},
|
| 30126 |
+
{
|
| 30127 |
+
"epoch": 4.9014245014245015,
|
| 30128 |
+
"grad_norm": 0.16464246809482574,
|
| 30129 |
+
"learning_rate": 4.4584114615575615e-05,
|
| 30130 |
+
"loss": 0.8007,
|
| 30131 |
+
"step": 4303
|
| 30132 |
+
},
|
| 30133 |
+
{
|
| 30134 |
+
"epoch": 4.902564102564103,
|
| 30135 |
+
"grad_norm": 0.19122007489204407,
|
| 30136 |
+
"learning_rate": 4.4581218303266935e-05,
|
| 30137 |
+
"loss": 0.7734,
|
| 30138 |
+
"step": 4304
|
| 30139 |
+
},
|
| 30140 |
+
{
|
| 30141 |
+
"epoch": 4.9037037037037035,
|
| 30142 |
+
"grad_norm": 0.17448489367961884,
|
| 30143 |
+
"learning_rate": 4.4578321310848695e-05,
|
| 30144 |
+
"loss": 0.815,
|
| 30145 |
+
"step": 4305
|
| 30146 |
+
},
|
| 30147 |
+
{
|
| 30148 |
+
"epoch": 4.904843304843305,
|
| 30149 |
+
"grad_norm": 0.17270396649837494,
|
| 30150 |
+
"learning_rate": 4.457542363842151e-05,
|
| 30151 |
+
"loss": 0.8,
|
| 30152 |
+
"step": 4306
|
| 30153 |
+
},
|
| 30154 |
+
{
|
| 30155 |
+
"epoch": 4.905982905982906,
|
| 30156 |
+
"grad_norm": 0.1664361208677292,
|
| 30157 |
+
"learning_rate": 4.4572525286086024e-05,
|
| 30158 |
+
"loss": 0.9305,
|
| 30159 |
+
"step": 4307
|
| 30160 |
+
},
|
| 30161 |
+
{
|
| 30162 |
+
"epoch": 4.907122507122507,
|
| 30163 |
+
"grad_norm": 0.1542702615261078,
|
| 30164 |
+
"learning_rate": 4.456962625394292e-05,
|
| 30165 |
+
"loss": 0.9192,
|
| 30166 |
+
"step": 4308
|
| 30167 |
+
},
|
| 30168 |
+
{
|
| 30169 |
+
"epoch": 4.908262108262108,
|
| 30170 |
+
"grad_norm": 0.1896369904279709,
|
| 30171 |
+
"learning_rate": 4.456672654209287e-05,
|
| 30172 |
+
"loss": 0.7259,
|
| 30173 |
+
"step": 4309
|
| 30174 |
+
},
|
| 30175 |
+
{
|
| 30176 |
+
"epoch": 4.90940170940171,
|
| 30177 |
+
"grad_norm": 0.14200268685817719,
|
| 30178 |
+
"learning_rate": 4.45638261506366e-05,
|
| 30179 |
+
"loss": 0.9892,
|
| 30180 |
+
"step": 4310
|
| 30181 |
+
},
|
| 30182 |
+
{
|
| 30183 |
+
"epoch": 4.91054131054131,
|
| 30184 |
+
"grad_norm": 0.1676367223262787,
|
| 30185 |
+
"learning_rate": 4.456092507967486e-05,
|
| 30186 |
+
"loss": 0.7585,
|
| 30187 |
+
"step": 4311
|
| 30188 |
+
},
|
| 30189 |
+
{
|
| 30190 |
+
"epoch": 4.911680911680912,
|
| 30191 |
+
"grad_norm": 0.174367755651474,
|
| 30192 |
+
"learning_rate": 4.455802332930839e-05,
|
| 30193 |
+
"loss": 0.868,
|
| 30194 |
+
"step": 4312
|
| 30195 |
+
},
|
| 30196 |
+
{
|
| 30197 |
+
"epoch": 4.912820512820513,
|
| 30198 |
+
"grad_norm": 0.1585119068622589,
|
| 30199 |
+
"learning_rate": 4.455512089963798e-05,
|
| 30200 |
+
"loss": 0.8462,
|
| 30201 |
+
"step": 4313
|
| 30202 |
+
},
|
| 30203 |
+
{
|
| 30204 |
+
"epoch": 4.913960113960114,
|
| 30205 |
+
"grad_norm": 0.16577641665935516,
|
| 30206 |
+
"learning_rate": 4.455221779076446e-05,
|
| 30207 |
+
"loss": 0.7259,
|
| 30208 |
+
"step": 4314
|
| 30209 |
+
},
|
| 30210 |
+
{
|
| 30211 |
+
"epoch": 4.915099715099715,
|
| 30212 |
+
"grad_norm": 0.15881091356277466,
|
| 30213 |
+
"learning_rate": 4.454931400278863e-05,
|
| 30214 |
+
"loss": 0.8301,
|
| 30215 |
+
"step": 4315
|
| 30216 |
+
},
|
| 30217 |
+
{
|
| 30218 |
+
"epoch": 4.9162393162393165,
|
| 30219 |
+
"grad_norm": 0.14386670291423798,
|
| 30220 |
+
"learning_rate": 4.4546409535811374e-05,
|
| 30221 |
+
"loss": 0.732,
|
| 30222 |
+
"step": 4316
|
| 30223 |
+
},
|
| 30224 |
+
{
|
| 30225 |
+
"epoch": 4.917378917378917,
|
| 30226 |
+
"grad_norm": 0.18718674778938293,
|
| 30227 |
+
"learning_rate": 4.454350438993356e-05,
|
| 30228 |
+
"loss": 0.6544,
|
| 30229 |
+
"step": 4317
|
| 30230 |
+
},
|
| 30231 |
+
{
|
| 30232 |
+
"epoch": 4.9185185185185185,
|
| 30233 |
+
"grad_norm": 0.15518997609615326,
|
| 30234 |
+
"learning_rate": 4.4540598565256093e-05,
|
| 30235 |
+
"loss": 0.8085,
|
| 30236 |
+
"step": 4318
|
| 30237 |
+
},
|
| 30238 |
+
{
|
| 30239 |
+
"epoch": 4.91965811965812,
|
| 30240 |
+
"grad_norm": 0.16699695587158203,
|
| 30241 |
+
"learning_rate": 4.45376920618799e-05,
|
| 30242 |
+
"loss": 0.7404,
|
| 30243 |
+
"step": 4319
|
| 30244 |
+
},
|
| 30245 |
+
{
|
| 30246 |
+
"epoch": 4.9207977207977205,
|
| 30247 |
+
"grad_norm": 0.14701253175735474,
|
| 30248 |
+
"learning_rate": 4.453478487990593e-05,
|
| 30249 |
+
"loss": 0.8182,
|
| 30250 |
+
"step": 4320
|
| 30251 |
+
},
|
| 30252 |
+
{
|
| 30253 |
+
"epoch": 4.921937321937322,
|
| 30254 |
+
"grad_norm": 0.16137848794460297,
|
| 30255 |
+
"learning_rate": 4.453187701943516e-05,
|
| 30256 |
+
"loss": 0.8008,
|
| 30257 |
+
"step": 4321
|
| 30258 |
+
},
|
| 30259 |
+
{
|
| 30260 |
+
"epoch": 4.923076923076923,
|
| 30261 |
+
"grad_norm": 0.1766296625137329,
|
| 30262 |
+
"learning_rate": 4.45289684805686e-05,
|
| 30263 |
+
"loss": 0.6583,
|
| 30264 |
+
"step": 4322
|
| 30265 |
+
},
|
| 30266 |
+
{
|
| 30267 |
+
"epoch": 4.924216524216524,
|
| 30268 |
+
"grad_norm": 0.18904195725917816,
|
| 30269 |
+
"learning_rate": 4.452605926340725e-05,
|
| 30270 |
+
"loss": 0.8189,
|
| 30271 |
+
"step": 4323
|
| 30272 |
+
},
|
| 30273 |
+
{
|
| 30274 |
+
"epoch": 4.925356125356125,
|
| 30275 |
+
"grad_norm": 0.15321408212184906,
|
| 30276 |
+
"learning_rate": 4.452314936805217e-05,
|
| 30277 |
+
"loss": 0.8261,
|
| 30278 |
+
"step": 4324
|
| 30279 |
+
},
|
| 30280 |
+
{
|
| 30281 |
+
"epoch": 4.926495726495727,
|
| 30282 |
+
"grad_norm": 0.16038638353347778,
|
| 30283 |
+
"learning_rate": 4.452023879460442e-05,
|
| 30284 |
+
"loss": 0.7155,
|
| 30285 |
+
"step": 4325
|
| 30286 |
+
},
|
| 30287 |
+
{
|
| 30288 |
+
"epoch": 4.927635327635327,
|
| 30289 |
+
"grad_norm": 0.14061199128627777,
|
| 30290 |
+
"learning_rate": 4.45173275431651e-05,
|
| 30291 |
+
"loss": 0.9511,
|
| 30292 |
+
"step": 4326
|
| 30293 |
+
},
|
| 30294 |
+
{
|
| 30295 |
+
"epoch": 4.928774928774929,
|
| 30296 |
+
"grad_norm": 0.19432227313518524,
|
| 30297 |
+
"learning_rate": 4.4514415613835313e-05,
|
| 30298 |
+
"loss": 0.6133,
|
| 30299 |
+
"step": 4327
|
| 30300 |
+
},
|
| 30301 |
+
{
|
| 30302 |
+
"epoch": 4.92991452991453,
|
| 30303 |
+
"grad_norm": 0.1387859731912613,
|
| 30304 |
+
"learning_rate": 4.4511503006716216e-05,
|
| 30305 |
+
"loss": 0.8883,
|
| 30306 |
+
"step": 4328
|
| 30307 |
+
},
|
| 30308 |
+
{
|
| 30309 |
+
"epoch": 4.931054131054131,
|
| 30310 |
+
"grad_norm": 0.15362222492694855,
|
| 30311 |
+
"learning_rate": 4.4508589721908955e-05,
|
| 30312 |
+
"loss": 0.843,
|
| 30313 |
+
"step": 4329
|
| 30314 |
+
},
|
| 30315 |
+
{
|
| 30316 |
+
"epoch": 4.932193732193732,
|
| 30317 |
+
"grad_norm": 0.15109822154045105,
|
| 30318 |
+
"learning_rate": 4.450567575951473e-05,
|
| 30319 |
+
"loss": 0.9899,
|
| 30320 |
+
"step": 4330
|
| 30321 |
+
},
|
| 30322 |
+
{
|
| 30323 |
+
"epoch": 4.933333333333334,
|
| 30324 |
+
"grad_norm": 0.18527065217494965,
|
| 30325 |
+
"learning_rate": 4.450276111963474e-05,
|
| 30326 |
+
"loss": 0.7677,
|
| 30327 |
+
"step": 4331
|
| 30328 |
+
},
|
| 30329 |
+
{
|
| 30330 |
+
"epoch": 4.934472934472934,
|
| 30331 |
+
"grad_norm": 0.13956625759601593,
|
| 30332 |
+
"learning_rate": 4.449984580237023e-05,
|
| 30333 |
+
"loss": 0.9034,
|
| 30334 |
+
"step": 4332
|
| 30335 |
+
},
|
| 30336 |
+
{
|
| 30337 |
+
"epoch": 4.9356125356125355,
|
| 30338 |
+
"grad_norm": 0.1639336198568344,
|
| 30339 |
+
"learning_rate": 4.449692980782244e-05,
|
| 30340 |
+
"loss": 0.8179,
|
| 30341 |
+
"step": 4333
|
| 30342 |
+
},
|
| 30343 |
+
{
|
| 30344 |
+
"epoch": 4.936752136752137,
|
| 30345 |
+
"grad_norm": 0.17157134413719177,
|
| 30346 |
+
"learning_rate": 4.449401313609267e-05,
|
| 30347 |
+
"loss": 0.6158,
|
| 30348 |
+
"step": 4334
|
| 30349 |
+
},
|
| 30350 |
+
{
|
| 30351 |
+
"epoch": 4.9378917378917375,
|
| 30352 |
+
"grad_norm": 0.14175517857074738,
|
| 30353 |
+
"learning_rate": 4.449109578728221e-05,
|
| 30354 |
+
"loss": 0.7851,
|
| 30355 |
+
"step": 4335
|
| 30356 |
+
},
|
| 30357 |
+
{
|
| 30358 |
+
"epoch": 4.939031339031339,
|
| 30359 |
+
"grad_norm": 0.17257359623908997,
|
| 30360 |
+
"learning_rate": 4.44881777614924e-05,
|
| 30361 |
+
"loss": 0.7213,
|
| 30362 |
+
"step": 4336
|
| 30363 |
+
},
|
| 30364 |
+
{
|
| 30365 |
+
"epoch": 4.94017094017094,
|
| 30366 |
+
"grad_norm": 0.18445263803005219,
|
| 30367 |
+
"learning_rate": 4.448525905882458e-05,
|
| 30368 |
+
"loss": 0.8393,
|
| 30369 |
+
"step": 4337
|
| 30370 |
+
},
|
| 30371 |
+
{
|
| 30372 |
+
"epoch": 4.941310541310541,
|
| 30373 |
+
"grad_norm": 0.1446041762828827,
|
| 30374 |
+
"learning_rate": 4.448233967938012e-05,
|
| 30375 |
+
"loss": 0.9169,
|
| 30376 |
+
"step": 4338
|
| 30377 |
+
},
|
| 30378 |
+
{
|
| 30379 |
+
"epoch": 4.942450142450142,
|
| 30380 |
+
"grad_norm": 0.15681029856204987,
|
| 30381 |
+
"learning_rate": 4.447941962326044e-05,
|
| 30382 |
+
"loss": 0.8487,
|
| 30383 |
+
"step": 4339
|
| 30384 |
+
},
|
| 30385 |
+
{
|
| 30386 |
+
"epoch": 4.943589743589744,
|
| 30387 |
+
"grad_norm": 0.15423312783241272,
|
| 30388 |
+
"learning_rate": 4.4476498890566946e-05,
|
| 30389 |
+
"loss": 0.7903,
|
| 30390 |
+
"step": 4340
|
| 30391 |
+
},
|
| 30392 |
+
{
|
| 30393 |
+
"epoch": 4.944729344729344,
|
| 30394 |
+
"grad_norm": 0.1776115745306015,
|
| 30395 |
+
"learning_rate": 4.4473577481401077e-05,
|
| 30396 |
+
"loss": 0.7179,
|
| 30397 |
+
"step": 4341
|
| 30398 |
+
},
|
| 30399 |
+
{
|
| 30400 |
+
"epoch": 4.945868945868946,
|
| 30401 |
+
"grad_norm": 0.1941158026456833,
|
| 30402 |
+
"learning_rate": 4.4470655395864315e-05,
|
| 30403 |
+
"loss": 0.7338,
|
| 30404 |
+
"step": 4342
|
| 30405 |
+
},
|
| 30406 |
+
{
|
| 30407 |
+
"epoch": 4.947008547008547,
|
| 30408 |
+
"grad_norm": 0.1917916089296341,
|
| 30409 |
+
"learning_rate": 4.446773263405814e-05,
|
| 30410 |
+
"loss": 0.6661,
|
| 30411 |
+
"step": 4343
|
| 30412 |
+
},
|
| 30413 |
+
{
|
| 30414 |
+
"epoch": 4.948148148148148,
|
| 30415 |
+
"grad_norm": 0.2219989150762558,
|
| 30416 |
+
"learning_rate": 4.446480919608408e-05,
|
| 30417 |
+
"loss": 0.5835,
|
| 30418 |
+
"step": 4344
|
| 30419 |
+
},
|
| 30420 |
+
{
|
| 30421 |
+
"epoch": 4.949287749287749,
|
| 30422 |
+
"grad_norm": 0.13458289206027985,
|
| 30423 |
+
"learning_rate": 4.4461885082043666e-05,
|
| 30424 |
+
"loss": 0.8697,
|
| 30425 |
+
"step": 4345
|
| 30426 |
+
},
|
| 30427 |
+
{
|
| 30428 |
+
"epoch": 4.950427350427351,
|
| 30429 |
+
"grad_norm": 0.21749819815158844,
|
| 30430 |
+
"learning_rate": 4.445896029203847e-05,
|
| 30431 |
+
"loss": 0.4783,
|
| 30432 |
+
"step": 4346
|
| 30433 |
+
},
|
| 30434 |
+
{
|
| 30435 |
+
"epoch": 4.951566951566951,
|
| 30436 |
+
"grad_norm": 0.1451740562915802,
|
| 30437 |
+
"learning_rate": 4.4456034826170054e-05,
|
| 30438 |
+
"loss": 0.8084,
|
| 30439 |
+
"step": 4347
|
| 30440 |
+
},
|
| 30441 |
+
{
|
| 30442 |
+
"epoch": 4.952706552706553,
|
| 30443 |
+
"grad_norm": 0.16358816623687744,
|
| 30444 |
+
"learning_rate": 4.4453108684540056e-05,
|
| 30445 |
+
"loss": 0.8031,
|
| 30446 |
+
"step": 4348
|
| 30447 |
+
},
|
| 30448 |
+
{
|
| 30449 |
+
"epoch": 4.953846153846154,
|
| 30450 |
+
"grad_norm": 0.1640550196170807,
|
| 30451 |
+
"learning_rate": 4.44501818672501e-05,
|
| 30452 |
+
"loss": 0.7792,
|
| 30453 |
+
"step": 4349
|
| 30454 |
+
},
|
| 30455 |
+
{
|
| 30456 |
+
"epoch": 4.9549857549857546,
|
| 30457 |
+
"grad_norm": 0.1569184958934784,
|
| 30458 |
+
"learning_rate": 4.4447254374401835e-05,
|
| 30459 |
+
"loss": 0.8447,
|
| 30460 |
+
"step": 4350
|
| 30461 |
+
},
|
| 30462 |
+
{
|
| 30463 |
+
"epoch": 4.956125356125356,
|
| 30464 |
+
"grad_norm": 0.1534481942653656,
|
| 30465 |
+
"learning_rate": 4.444432620609694e-05,
|
| 30466 |
+
"loss": 0.8901,
|
| 30467 |
+
"step": 4351
|
| 30468 |
+
},
|
| 30469 |
+
{
|
| 30470 |
+
"epoch": 4.957264957264957,
|
| 30471 |
+
"grad_norm": 0.17017418146133423,
|
| 30472 |
+
"learning_rate": 4.4441397362437134e-05,
|
| 30473 |
+
"loss": 0.7446,
|
| 30474 |
+
"step": 4352
|
| 30475 |
+
},
|
| 30476 |
+
{
|
| 30477 |
+
"epoch": 4.958404558404558,
|
| 30478 |
+
"grad_norm": 0.228437602519989,
|
| 30479 |
+
"learning_rate": 4.443846784352413e-05,
|
| 30480 |
+
"loss": 0.6382,
|
| 30481 |
+
"step": 4353
|
| 30482 |
+
},
|
| 30483 |
+
{
|
| 30484 |
+
"epoch": 4.959544159544159,
|
| 30485 |
+
"grad_norm": 0.1891854703426361,
|
| 30486 |
+
"learning_rate": 4.443553764945968e-05,
|
| 30487 |
+
"loss": 0.7518,
|
| 30488 |
+
"step": 4354
|
| 30489 |
+
},
|
| 30490 |
+
{
|
| 30491 |
+
"epoch": 4.960683760683761,
|
| 30492 |
+
"grad_norm": 0.16365045309066772,
|
| 30493 |
+
"learning_rate": 4.443260678034555e-05,
|
| 30494 |
+
"loss": 0.8451,
|
| 30495 |
+
"step": 4355
|
| 30496 |
+
},
|
| 30497 |
+
{
|
| 30498 |
+
"epoch": 4.961823361823361,
|
| 30499 |
+
"grad_norm": 0.1816239207983017,
|
| 30500 |
+
"learning_rate": 4.4429675236283565e-05,
|
| 30501 |
+
"loss": 0.6822,
|
| 30502 |
+
"step": 4356
|
| 30503 |
+
},
|
| 30504 |
+
{
|
| 30505 |
+
"epoch": 4.962962962962963,
|
| 30506 |
+
"grad_norm": 0.18229347467422485,
|
| 30507 |
+
"learning_rate": 4.4426743017375516e-05,
|
| 30508 |
+
"loss": 0.6843,
|
| 30509 |
+
"step": 4357
|
| 30510 |
+
},
|
| 30511 |
+
{
|
| 30512 |
+
"epoch": 4.964102564102564,
|
| 30513 |
+
"grad_norm": 0.15037180483341217,
|
| 30514 |
+
"learning_rate": 4.4423810123723264e-05,
|
| 30515 |
+
"loss": 0.8652,
|
| 30516 |
+
"step": 4358
|
| 30517 |
+
},
|
| 30518 |
+
{
|
| 30519 |
+
"epoch": 4.965242165242165,
|
| 30520 |
+
"grad_norm": 0.14027701318264008,
|
| 30521 |
+
"learning_rate": 4.442087655542867e-05,
|
| 30522 |
+
"loss": 0.8458,
|
| 30523 |
+
"step": 4359
|
| 30524 |
+
},
|
| 30525 |
+
{
|
| 30526 |
+
"epoch": 4.966381766381766,
|
| 30527 |
+
"grad_norm": 0.1816105842590332,
|
| 30528 |
+
"learning_rate": 4.441794231259362e-05,
|
| 30529 |
+
"loss": 0.7752,
|
| 30530 |
+
"step": 4360
|
| 30531 |
+
},
|
| 30532 |
+
{
|
| 30533 |
+
"epoch": 4.967521367521368,
|
| 30534 |
+
"grad_norm": 0.17853955924510956,
|
| 30535 |
+
"learning_rate": 4.441500739532004e-05,
|
| 30536 |
+
"loss": 0.7008,
|
| 30537 |
+
"step": 4361
|
| 30538 |
+
},
|
| 30539 |
+
{
|
| 30540 |
+
"epoch": 4.968660968660968,
|
| 30541 |
+
"grad_norm": 0.1522316336631775,
|
| 30542 |
+
"learning_rate": 4.441207180370986e-05,
|
| 30543 |
+
"loss": 0.8782,
|
| 30544 |
+
"step": 4362
|
| 30545 |
+
},
|
| 30546 |
+
{
|
| 30547 |
+
"epoch": 4.96980056980057,
|
| 30548 |
+
"grad_norm": 0.1653551161289215,
|
| 30549 |
+
"learning_rate": 4.4409135537865044e-05,
|
| 30550 |
+
"loss": 0.754,
|
| 30551 |
+
"step": 4363
|
| 30552 |
+
},
|
| 30553 |
+
{
|
| 30554 |
+
"epoch": 4.970940170940171,
|
| 30555 |
+
"grad_norm": 0.18796348571777344,
|
| 30556 |
+
"learning_rate": 4.4406198597887574e-05,
|
| 30557 |
+
"loss": 0.7707,
|
| 30558 |
+
"step": 4364
|
| 30559 |
+
},
|
| 30560 |
+
{
|
| 30561 |
+
"epoch": 4.972079772079772,
|
| 30562 |
+
"grad_norm": 0.1707884967327118,
|
| 30563 |
+
"learning_rate": 4.440326098387946e-05,
|
| 30564 |
+
"loss": 0.84,
|
| 30565 |
+
"step": 4365
|
| 30566 |
+
},
|
| 30567 |
+
{
|
| 30568 |
+
"epoch": 4.973219373219373,
|
| 30569 |
+
"grad_norm": 0.16822636127471924,
|
| 30570 |
+
"learning_rate": 4.440032269594272e-05,
|
| 30571 |
+
"loss": 0.7032,
|
| 30572 |
+
"step": 4366
|
| 30573 |
+
},
|
| 30574 |
+
{
|
| 30575 |
+
"epoch": 4.9743589743589745,
|
| 30576 |
+
"grad_norm": 0.20402517914772034,
|
| 30577 |
+
"learning_rate": 4.4397383734179444e-05,
|
| 30578 |
+
"loss": 0.6482,
|
| 30579 |
+
"step": 4367
|
| 30580 |
+
},
|
| 30581 |
+
{
|
| 30582 |
+
"epoch": 4.975498575498576,
|
| 30583 |
+
"grad_norm": 0.20499737560749054,
|
| 30584 |
+
"learning_rate": 4.4394444098691675e-05,
|
| 30585 |
+
"loss": 0.5707,
|
| 30586 |
+
"step": 4368
|
| 30587 |
+
},
|
| 30588 |
+
{
|
| 30589 |
+
"epoch": 4.976638176638176,
|
| 30590 |
+
"grad_norm": 0.16235454380512238,
|
| 30591 |
+
"learning_rate": 4.4391503789581526e-05,
|
| 30592 |
+
"loss": 0.8344,
|
| 30593 |
+
"step": 4369
|
| 30594 |
+
},
|
| 30595 |
+
{
|
| 30596 |
+
"epoch": 4.977777777777778,
|
| 30597 |
+
"grad_norm": 0.14869852364063263,
|
| 30598 |
+
"learning_rate": 4.438856280695113e-05,
|
| 30599 |
+
"loss": 0.9471,
|
| 30600 |
+
"step": 4370
|
| 30601 |
+
},
|
| 30602 |
+
{
|
| 30603 |
+
"epoch": 4.978917378917379,
|
| 30604 |
+
"grad_norm": 0.17793439328670502,
|
| 30605 |
+
"learning_rate": 4.438562115090262e-05,
|
| 30606 |
+
"loss": 0.7396,
|
| 30607 |
+
"step": 4371
|
| 30608 |
+
},
|
| 30609 |
+
{
|
| 30610 |
+
"epoch": 4.98005698005698,
|
| 30611 |
+
"grad_norm": 0.15897755324840546,
|
| 30612 |
+
"learning_rate": 4.4382678821538195e-05,
|
| 30613 |
+
"loss": 0.7443,
|
| 30614 |
+
"step": 4372
|
| 30615 |
+
},
|
| 30616 |
+
{
|
| 30617 |
+
"epoch": 4.981196581196581,
|
| 30618 |
+
"grad_norm": 0.1621100902557373,
|
| 30619 |
+
"learning_rate": 4.437973581896001e-05,
|
| 30620 |
+
"loss": 0.8844,
|
| 30621 |
+
"step": 4373
|
| 30622 |
+
},
|
| 30623 |
+
{
|
| 30624 |
+
"epoch": 4.982336182336183,
|
| 30625 |
+
"grad_norm": 0.1932118684053421,
|
| 30626 |
+
"learning_rate": 4.437679214327032e-05,
|
| 30627 |
+
"loss": 0.7382,
|
| 30628 |
+
"step": 4374
|
| 30629 |
+
},
|
| 30630 |
+
{
|
| 30631 |
+
"epoch": 4.983475783475783,
|
| 30632 |
+
"grad_norm": 0.16252288222312927,
|
| 30633 |
+
"learning_rate": 4.4373847794571346e-05,
|
| 30634 |
+
"loss": 0.7316,
|
| 30635 |
+
"step": 4375
|
| 30636 |
+
},
|
| 30637 |
+
{
|
| 30638 |
+
"epoch": 4.984615384615385,
|
| 30639 |
+
"grad_norm": 0.17581906914710999,
|
| 30640 |
+
"learning_rate": 4.437090277296536e-05,
|
| 30641 |
+
"loss": 0.7582,
|
| 30642 |
+
"step": 4376
|
| 30643 |
+
},
|
| 30644 |
+
{
|
| 30645 |
+
"epoch": 4.985754985754986,
|
| 30646 |
+
"grad_norm": 0.16340146958827972,
|
| 30647 |
+
"learning_rate": 4.436795707855466e-05,
|
| 30648 |
+
"loss": 0.7943,
|
| 30649 |
+
"step": 4377
|
| 30650 |
+
},
|
| 30651 |
+
{
|
| 30652 |
+
"epoch": 4.986894586894587,
|
| 30653 |
+
"grad_norm": 0.14689506590366364,
|
| 30654 |
+
"learning_rate": 4.436501071144153e-05,
|
| 30655 |
+
"loss": 0.8851,
|
| 30656 |
+
"step": 4378
|
| 30657 |
+
},
|
| 30658 |
+
{
|
| 30659 |
+
"epoch": 4.988034188034188,
|
| 30660 |
+
"grad_norm": 0.17721427977085114,
|
| 30661 |
+
"learning_rate": 4.4362063671728344e-05,
|
| 30662 |
+
"loss": 0.7815,
|
| 30663 |
+
"step": 4379
|
| 30664 |
+
},
|
| 30665 |
+
{
|
| 30666 |
+
"epoch": 4.9891737891737895,
|
| 30667 |
+
"grad_norm": 0.18198640644550323,
|
| 30668 |
+
"learning_rate": 4.4359115959517426e-05,
|
| 30669 |
+
"loss": 0.6887,
|
| 30670 |
+
"step": 4380
|
| 30671 |
+
},
|
| 30672 |
+
{
|
| 30673 |
+
"epoch": 4.99031339031339,
|
| 30674 |
+
"grad_norm": 0.17018204927444458,
|
| 30675 |
+
"learning_rate": 4.435616757491118e-05,
|
| 30676 |
+
"loss": 0.8557,
|
| 30677 |
+
"step": 4381
|
| 30678 |
+
},
|
| 30679 |
+
{
|
| 30680 |
+
"epoch": 4.9914529914529915,
|
| 30681 |
+
"grad_norm": 0.15465298295021057,
|
| 30682 |
+
"learning_rate": 4.435321851801201e-05,
|
| 30683 |
+
"loss": 0.8588,
|
| 30684 |
+
"step": 4382
|
| 30685 |
+
},
|
| 30686 |
+
{
|
| 30687 |
+
"epoch": 4.992592592592593,
|
| 30688 |
+
"grad_norm": 0.18045377731323242,
|
| 30689 |
+
"learning_rate": 4.435026878892233e-05,
|
| 30690 |
+
"loss": 0.6417,
|
| 30691 |
+
"step": 4383
|
| 30692 |
+
},
|
| 30693 |
+
{
|
| 30694 |
+
"epoch": 4.9937321937321935,
|
| 30695 |
+
"grad_norm": 0.16702929139137268,
|
| 30696 |
+
"learning_rate": 4.43473183877446e-05,
|
| 30697 |
+
"loss": 0.8219,
|
| 30698 |
+
"step": 4384
|
| 30699 |
+
},
|
| 30700 |
+
{
|
| 30701 |
+
"epoch": 4.994871794871795,
|
| 30702 |
+
"grad_norm": 0.18059112131595612,
|
| 30703 |
+
"learning_rate": 4.4344367314581306e-05,
|
| 30704 |
+
"loss": 0.8059,
|
| 30705 |
+
"step": 4385
|
| 30706 |
+
},
|
| 30707 |
+
{
|
| 30708 |
+
"epoch": 4.996011396011396,
|
| 30709 |
+
"grad_norm": 0.14532163739204407,
|
| 30710 |
+
"learning_rate": 4.434141556953493e-05,
|
| 30711 |
+
"loss": 0.8521,
|
| 30712 |
+
"step": 4386
|
| 30713 |
+
},
|
| 30714 |
+
{
|
| 30715 |
+
"epoch": 4.997150997150997,
|
| 30716 |
+
"grad_norm": 0.180996835231781,
|
| 30717 |
+
"learning_rate": 4.433846315270801e-05,
|
| 30718 |
+
"loss": 0.8699,
|
| 30719 |
+
"step": 4387
|
| 30720 |
+
},
|
| 30721 |
+
{
|
| 30722 |
+
"epoch": 4.998290598290598,
|
| 30723 |
+
"grad_norm": 0.19515706598758698,
|
| 30724 |
+
"learning_rate": 4.433551006420308e-05,
|
| 30725 |
+
"loss": 0.6812,
|
| 30726 |
+
"step": 4388
|
| 30727 |
+
},
|
| 30728 |
+
{
|
| 30729 |
+
"epoch": 4.9994301994302,
|
| 30730 |
+
"grad_norm": 0.18740420043468475,
|
| 30731 |
+
"learning_rate": 4.433255630412271e-05,
|
| 30732 |
+
"loss": 0.7503,
|
| 30733 |
+
"step": 4389
|
| 30734 |
+
},
|
| 30735 |
+
{
|
| 30736 |
+
"epoch": 5.0,
|
| 30737 |
+
"grad_norm": 0.2839340567588806,
|
| 30738 |
+
"learning_rate": 4.432960187256949e-05,
|
| 30739 |
+
"loss": 1.0157,
|
| 30740 |
+
"step": 4390
|
| 30741 |
+
},
|
| 30742 |
+
{
|
| 30743 |
+
"epoch": 5.001139601139601,
|
| 30744 |
+
"grad_norm": 0.18848787248134613,
|
| 30745 |
+
"learning_rate": 4.4326646769646055e-05,
|
| 30746 |
+
"loss": 0.7713,
|
| 30747 |
+
"step": 4391
|
| 30748 |
+
},
|
| 30749 |
+
{
|
| 30750 |
+
"epoch": 5.002279202279202,
|
| 30751 |
+
"grad_norm": 0.19647054374217987,
|
| 30752 |
+
"learning_rate": 4.432369099545502e-05,
|
| 30753 |
+
"loss": 0.734,
|
| 30754 |
+
"step": 4392
|
| 30755 |
+
},
|
| 30756 |
+
{
|
| 30757 |
+
"epoch": 5.003418803418803,
|
| 30758 |
+
"grad_norm": 0.14491033554077148,
|
| 30759 |
+
"learning_rate": 4.432073455009905e-05,
|
| 30760 |
+
"loss": 0.7236,
|
| 30761 |
+
"step": 4393
|
| 30762 |
+
},
|
| 30763 |
+
{
|
| 30764 |
+
"epoch": 5.004558404558405,
|
| 30765 |
+
"grad_norm": 0.16267147660255432,
|
| 30766 |
+
"learning_rate": 4.431777743368085e-05,
|
| 30767 |
+
"loss": 1.0218,
|
| 30768 |
+
"step": 4394
|
| 30769 |
+
},
|
| 30770 |
+
{
|
| 30771 |
+
"epoch": 5.005698005698005,
|
| 30772 |
+
"grad_norm": 0.1726360023021698,
|
| 30773 |
+
"learning_rate": 4.431481964630311e-05,
|
| 30774 |
+
"loss": 0.7848,
|
| 30775 |
+
"step": 4395
|
| 30776 |
+
},
|
| 30777 |
+
{
|
| 30778 |
+
"epoch": 5.006837606837607,
|
| 30779 |
+
"grad_norm": 0.16114525496959686,
|
| 30780 |
+
"learning_rate": 4.431186118806857e-05,
|
| 30781 |
+
"loss": 0.9004,
|
| 30782 |
+
"step": 4396
|
| 30783 |
+
},
|
| 30784 |
+
{
|
| 30785 |
+
"epoch": 5.007977207977208,
|
| 30786 |
+
"grad_norm": 0.161496102809906,
|
| 30787 |
+
"learning_rate": 4.4308902059079976e-05,
|
| 30788 |
+
"loss": 0.9281,
|
| 30789 |
+
"step": 4397
|
| 30790 |
+
},
|
| 30791 |
+
{
|
| 30792 |
+
"epoch": 5.009116809116809,
|
| 30793 |
+
"grad_norm": 0.16877681016921997,
|
| 30794 |
+
"learning_rate": 4.4305942259440114e-05,
|
| 30795 |
+
"loss": 0.9488,
|
| 30796 |
+
"step": 4398
|
| 30797 |
+
},
|
| 30798 |
+
{
|
| 30799 |
+
"epoch": 5.01025641025641,
|
| 30800 |
+
"grad_norm": 0.20223818719387054,
|
| 30801 |
+
"learning_rate": 4.4302981789251796e-05,
|
| 30802 |
+
"loss": 0.6802,
|
| 30803 |
+
"step": 4399
|
| 30804 |
+
},
|
| 30805 |
+
{
|
| 30806 |
+
"epoch": 5.011396011396012,
|
| 30807 |
+
"grad_norm": 0.16235707700252533,
|
| 30808 |
+
"learning_rate": 4.430002064861783e-05,
|
| 30809 |
+
"loss": 0.7991,
|
| 30810 |
+
"step": 4400
|
| 30811 |
+
},
|
| 30812 |
+
{
|
| 30813 |
+
"epoch": 5.012535612535612,
|
| 30814 |
+
"grad_norm": 0.18385708332061768,
|
| 30815 |
+
"learning_rate": 4.429705883764107e-05,
|
| 30816 |
+
"loss": 0.5843,
|
| 30817 |
+
"step": 4401
|
| 30818 |
+
},
|
| 30819 |
+
{
|
| 30820 |
+
"epoch": 5.013675213675214,
|
| 30821 |
+
"grad_norm": 0.17766490578651428,
|
| 30822 |
+
"learning_rate": 4.42940963564244e-05,
|
| 30823 |
+
"loss": 0.668,
|
| 30824 |
+
"step": 4402
|
| 30825 |
+
},
|
| 30826 |
+
{
|
| 30827 |
+
"epoch": 5.014814814814815,
|
| 30828 |
+
"grad_norm": 0.16907937824726105,
|
| 30829 |
+
"learning_rate": 4.429113320507069e-05,
|
| 30830 |
+
"loss": 0.7932,
|
| 30831 |
+
"step": 4403
|
| 30832 |
+
},
|
| 30833 |
+
{
|
| 30834 |
+
"epoch": 5.015954415954416,
|
| 30835 |
+
"grad_norm": 0.1943625956773758,
|
| 30836 |
+
"learning_rate": 4.428816938368288e-05,
|
| 30837 |
+
"loss": 0.7006,
|
| 30838 |
+
"step": 4404
|
| 30839 |
+
},
|
| 30840 |
+
{
|
| 30841 |
+
"epoch": 5.017094017094017,
|
| 30842 |
+
"grad_norm": 0.14672493934631348,
|
| 30843 |
+
"learning_rate": 4.4285204892363906e-05,
|
| 30844 |
+
"loss": 0.8476,
|
| 30845 |
+
"step": 4405
|
| 30846 |
+
},
|
| 30847 |
+
{
|
| 30848 |
+
"epoch": 5.0182336182336185,
|
| 30849 |
+
"grad_norm": 0.14297886192798615,
|
| 30850 |
+
"learning_rate": 4.428223973121673e-05,
|
| 30851 |
+
"loss": 1.0138,
|
| 30852 |
+
"step": 4406
|
| 30853 |
+
},
|
| 30854 |
+
{
|
| 30855 |
+
"epoch": 5.019373219373219,
|
| 30856 |
+
"grad_norm": 0.1751715987920761,
|
| 30857 |
+
"learning_rate": 4.427927390034434e-05,
|
| 30858 |
+
"loss": 0.7919,
|
| 30859 |
+
"step": 4407
|
| 30860 |
+
},
|
| 30861 |
+
{
|
| 30862 |
+
"epoch": 5.02051282051282,
|
| 30863 |
+
"grad_norm": 0.18038953840732574,
|
| 30864 |
+
"learning_rate": 4.427630739984975e-05,
|
| 30865 |
+
"loss": 0.802,
|
| 30866 |
+
"step": 4408
|
| 30867 |
+
},
|
| 30868 |
+
{
|
| 30869 |
+
"epoch": 5.021652421652422,
|
| 30870 |
+
"grad_norm": 0.1847195029258728,
|
| 30871 |
+
"learning_rate": 4.4273340229836e-05,
|
| 30872 |
+
"loss": 0.7227,
|
| 30873 |
+
"step": 4409
|
| 30874 |
+
},
|
| 30875 |
+
{
|
| 30876 |
+
"epoch": 5.022792022792022,
|
| 30877 |
+
"grad_norm": 0.22509942948818207,
|
| 30878 |
+
"learning_rate": 4.427037239040613e-05,
|
| 30879 |
+
"loss": 0.6507,
|
| 30880 |
+
"step": 4410
|
| 30881 |
+
},
|
| 30882 |
+
{
|
| 30883 |
+
"epoch": 5.023931623931624,
|
| 30884 |
+
"grad_norm": 0.1595267504453659,
|
| 30885 |
+
"learning_rate": 4.426740388166325e-05,
|
| 30886 |
+
"loss": 0.8574,
|
| 30887 |
+
"step": 4411
|
| 30888 |
+
},
|
| 30889 |
+
{
|
| 30890 |
+
"epoch": 5.025071225071225,
|
| 30891 |
+
"grad_norm": 0.2153182029724121,
|
| 30892 |
+
"learning_rate": 4.4264434703710435e-05,
|
| 30893 |
+
"loss": 0.6417,
|
| 30894 |
+
"step": 4412
|
| 30895 |
+
},
|
| 30896 |
+
{
|
| 30897 |
+
"epoch": 5.026210826210826,
|
| 30898 |
+
"grad_norm": 0.16790950298309326,
|
| 30899 |
+
"learning_rate": 4.426146485665083e-05,
|
| 30900 |
+
"loss": 0.8256,
|
| 30901 |
+
"step": 4413
|
| 30902 |
+
},
|
| 30903 |
+
{
|
| 30904 |
+
"epoch": 5.027350427350427,
|
| 30905 |
+
"grad_norm": 0.14109621942043304,
|
| 30906 |
+
"learning_rate": 4.425849434058758e-05,
|
| 30907 |
+
"loss": 0.8758,
|
| 30908 |
+
"step": 4414
|
| 30909 |
+
},
|
| 30910 |
+
{
|
| 30911 |
+
"epoch": 5.028490028490029,
|
| 30912 |
+
"grad_norm": 0.1420576125383377,
|
| 30913 |
+
"learning_rate": 4.425552315562386e-05,
|
| 30914 |
+
"loss": 0.7635,
|
| 30915 |
+
"step": 4415
|
| 30916 |
+
},
|
| 30917 |
+
{
|
| 30918 |
+
"epoch": 5.029629629629629,
|
| 30919 |
+
"grad_norm": 0.21221227943897247,
|
| 30920 |
+
"learning_rate": 4.425255130186287e-05,
|
| 30921 |
+
"loss": 0.6607,
|
| 30922 |
+
"step": 4416
|
| 30923 |
+
},
|
| 30924 |
+
{
|
| 30925 |
+
"epoch": 5.030769230769231,
|
| 30926 |
+
"grad_norm": 0.19328977167606354,
|
| 30927 |
+
"learning_rate": 4.424957877940782e-05,
|
| 30928 |
+
"loss": 0.5981,
|
| 30929 |
+
"step": 4417
|
| 30930 |
+
},
|
| 30931 |
+
{
|
| 30932 |
+
"epoch": 5.031908831908832,
|
| 30933 |
+
"grad_norm": 0.15180927515029907,
|
| 30934 |
+
"learning_rate": 4.4246605588361965e-05,
|
| 30935 |
+
"loss": 0.863,
|
| 30936 |
+
"step": 4418
|
| 30937 |
+
},
|
| 30938 |
+
{
|
| 30939 |
+
"epoch": 5.033048433048433,
|
| 30940 |
+
"grad_norm": 0.1497860550880432,
|
| 30941 |
+
"learning_rate": 4.424363172882858e-05,
|
| 30942 |
+
"loss": 0.7794,
|
| 30943 |
+
"step": 4419
|
| 30944 |
+
},
|
| 30945 |
+
{
|
| 30946 |
+
"epoch": 5.034188034188034,
|
| 30947 |
+
"grad_norm": 0.18027135729789734,
|
| 30948 |
+
"learning_rate": 4.424065720091094e-05,
|
| 30949 |
+
"loss": 0.7392,
|
| 30950 |
+
"step": 4420
|
| 30951 |
+
},
|
| 30952 |
+
{
|
| 30953 |
+
"epoch": 5.0353276353276355,
|
| 30954 |
+
"grad_norm": 0.17033274471759796,
|
| 30955 |
+
"learning_rate": 4.423768200471236e-05,
|
| 30956 |
+
"loss": 0.7714,
|
| 30957 |
+
"step": 4421
|
| 30958 |
+
},
|
| 30959 |
+
{
|
| 30960 |
+
"epoch": 5.036467236467236,
|
| 30961 |
+
"grad_norm": 0.16878366470336914,
|
| 30962 |
+
"learning_rate": 4.4234706140336176e-05,
|
| 30963 |
+
"loss": 0.7275,
|
| 30964 |
+
"step": 4422
|
| 30965 |
+
},
|
| 30966 |
+
{
|
| 30967 |
+
"epoch": 5.0376068376068375,
|
| 30968 |
+
"grad_norm": 0.13580316305160522,
|
| 30969 |
+
"learning_rate": 4.423172960788576e-05,
|
| 30970 |
+
"loss": 0.8921,
|
| 30971 |
+
"step": 4423
|
| 30972 |
+
},
|
| 30973 |
+
{
|
| 30974 |
+
"epoch": 5.038746438746439,
|
| 30975 |
+
"grad_norm": 0.17923130095005035,
|
| 30976 |
+
"learning_rate": 4.422875240746448e-05,
|
| 30977 |
+
"loss": 0.7384,
|
| 30978 |
+
"step": 4424
|
| 30979 |
+
},
|
| 30980 |
+
{
|
| 30981 |
+
"epoch": 5.0398860398860394,
|
| 30982 |
+
"grad_norm": 0.18059013783931732,
|
| 30983 |
+
"learning_rate": 4.422577453917576e-05,
|
| 30984 |
+
"loss": 0.8264,
|
| 30985 |
+
"step": 4425
|
| 30986 |
+
},
|
| 30987 |
+
{
|
| 30988 |
+
"epoch": 5.041025641025641,
|
| 30989 |
+
"grad_norm": 0.17888416349887848,
|
| 30990 |
+
"learning_rate": 4.422279600312301e-05,
|
| 30991 |
+
"loss": 0.6604,
|
| 30992 |
+
"step": 4426
|
| 30993 |
+
},
|
| 30994 |
+
{
|
| 30995 |
+
"epoch": 5.042165242165242,
|
| 30996 |
+
"grad_norm": 0.13452483713626862,
|
| 30997 |
+
"learning_rate": 4.4219816799409696e-05,
|
| 30998 |
+
"loss": 1.0043,
|
| 30999 |
+
"step": 4427
|
| 31000 |
+
},
|
| 31001 |
+
{
|
| 31002 |
+
"epoch": 5.043304843304844,
|
| 31003 |
+
"grad_norm": 0.17872373759746552,
|
| 31004 |
+
"learning_rate": 4.421683692813929e-05,
|
| 31005 |
+
"loss": 0.7793,
|
| 31006 |
+
"step": 4428
|
| 31007 |
+
},
|
| 31008 |
+
{
|
| 31009 |
+
"epoch": 5.044444444444444,
|
| 31010 |
+
"grad_norm": 0.19449970126152039,
|
| 31011 |
+
"learning_rate": 4.42138563894153e-05,
|
| 31012 |
+
"loss": 0.6775,
|
| 31013 |
+
"step": 4429
|
| 31014 |
+
},
|
| 31015 |
+
{
|
| 31016 |
+
"epoch": 5.045584045584046,
|
| 31017 |
+
"grad_norm": 0.17247280478477478,
|
| 31018 |
+
"learning_rate": 4.421087518334123e-05,
|
| 31019 |
+
"loss": 0.8989,
|
| 31020 |
+
"step": 4430
|
| 31021 |
+
},
|
| 31022 |
+
{
|
| 31023 |
+
"epoch": 5.046723646723647,
|
| 31024 |
+
"grad_norm": 0.16216397285461426,
|
| 31025 |
+
"learning_rate": 4.420789331002063e-05,
|
| 31026 |
+
"loss": 0.6729,
|
| 31027 |
+
"step": 4431
|
| 31028 |
+
},
|
| 31029 |
+
{
|
| 31030 |
+
"epoch": 5.047863247863248,
|
| 31031 |
+
"grad_norm": 0.17316816747188568,
|
| 31032 |
+
"learning_rate": 4.4204910769557075e-05,
|
| 31033 |
+
"loss": 0.7585,
|
| 31034 |
+
"step": 4432
|
| 31035 |
+
},
|
| 31036 |
+
{
|
| 31037 |
+
"epoch": 5.049002849002849,
|
| 31038 |
+
"grad_norm": 0.2130867838859558,
|
| 31039 |
+
"learning_rate": 4.4201927562054155e-05,
|
| 31040 |
+
"loss": 0.661,
|
| 31041 |
+
"step": 4433
|
| 31042 |
+
},
|
| 31043 |
+
{
|
| 31044 |
+
"epoch": 5.050142450142451,
|
| 31045 |
+
"grad_norm": 0.17586174607276917,
|
| 31046 |
+
"learning_rate": 4.419894368761549e-05,
|
| 31047 |
+
"loss": 0.6849,
|
| 31048 |
+
"step": 4434
|
| 31049 |
+
},
|
| 31050 |
+
{
|
| 31051 |
+
"epoch": 5.051282051282051,
|
| 31052 |
+
"grad_norm": 0.16294056177139282,
|
| 31053 |
+
"learning_rate": 4.419595914634471e-05,
|
| 31054 |
+
"loss": 0.7675,
|
| 31055 |
+
"step": 4435
|
| 31056 |
+
},
|
| 31057 |
+
{
|
| 31058 |
+
"epoch": 5.0524216524216525,
|
| 31059 |
+
"grad_norm": 0.147496297955513,
|
| 31060 |
+
"learning_rate": 4.4192973938345486e-05,
|
| 31061 |
+
"loss": 0.7813,
|
| 31062 |
+
"step": 4436
|
| 31063 |
+
},
|
| 31064 |
+
{
|
| 31065 |
+
"epoch": 5.053561253561254,
|
| 31066 |
+
"grad_norm": 0.15688002109527588,
|
| 31067 |
+
"learning_rate": 4.418998806372149e-05,
|
| 31068 |
+
"loss": 0.817,
|
| 31069 |
+
"step": 4437
|
| 31070 |
+
},
|
| 31071 |
+
{
|
| 31072 |
+
"epoch": 5.0547008547008545,
|
| 31073 |
+
"grad_norm": 0.14161467552185059,
|
| 31074 |
+
"learning_rate": 4.4187001522576447e-05,
|
| 31075 |
+
"loss": 0.8762,
|
| 31076 |
+
"step": 4438
|
| 31077 |
+
},
|
| 31078 |
+
{
|
| 31079 |
+
"epoch": 5.055840455840456,
|
| 31080 |
+
"grad_norm": 0.15354563295841217,
|
| 31081 |
+
"learning_rate": 4.418401431501407e-05,
|
| 31082 |
+
"loss": 0.8639,
|
| 31083 |
+
"step": 4439
|
| 31084 |
+
},
|
| 31085 |
+
{
|
| 31086 |
+
"epoch": 5.056980056980057,
|
| 31087 |
+
"grad_norm": 0.18183383345603943,
|
| 31088 |
+
"learning_rate": 4.418102644113811e-05,
|
| 31089 |
+
"loss": 0.7557,
|
| 31090 |
+
"step": 4440
|
| 31091 |
+
},
|
| 31092 |
+
{
|
| 31093 |
+
"epoch": 5.058119658119658,
|
| 31094 |
+
"grad_norm": 0.17570596933364868,
|
| 31095 |
+
"learning_rate": 4.417803790105236e-05,
|
| 31096 |
+
"loss": 0.8905,
|
| 31097 |
+
"step": 4441
|
| 31098 |
+
},
|
| 31099 |
+
{
|
| 31100 |
+
"epoch": 5.059259259259259,
|
| 31101 |
+
"grad_norm": 0.1544586569070816,
|
| 31102 |
+
"learning_rate": 4.417504869486061e-05,
|
| 31103 |
+
"loss": 0.7511,
|
| 31104 |
+
"step": 4442
|
| 31105 |
+
},
|
| 31106 |
+
{
|
| 31107 |
+
"epoch": 5.060398860398861,
|
| 31108 |
+
"grad_norm": 0.19254599511623383,
|
| 31109 |
+
"learning_rate": 4.41720588226667e-05,
|
| 31110 |
+
"loss": 0.8275,
|
| 31111 |
+
"step": 4443
|
| 31112 |
+
},
|
| 31113 |
+
{
|
| 31114 |
+
"epoch": 5.061538461538461,
|
| 31115 |
+
"grad_norm": 0.18347801268100739,
|
| 31116 |
+
"learning_rate": 4.416906828457446e-05,
|
| 31117 |
+
"loss": 0.6592,
|
| 31118 |
+
"step": 4444
|
| 31119 |
+
},
|
| 31120 |
+
{
|
| 31121 |
+
"epoch": 5.062678062678063,
|
| 31122 |
+
"grad_norm": 0.18191008269786835,
|
| 31123 |
+
"learning_rate": 4.416607708068775e-05,
|
| 31124 |
+
"loss": 0.7512,
|
| 31125 |
+
"step": 4445
|
| 31126 |
+
},
|
| 31127 |
+
{
|
| 31128 |
+
"epoch": 5.063817663817664,
|
| 31129 |
+
"grad_norm": 0.15872415900230408,
|
| 31130 |
+
"learning_rate": 4.416308521111049e-05,
|
| 31131 |
+
"loss": 0.9564,
|
| 31132 |
+
"step": 4446
|
| 31133 |
+
},
|
| 31134 |
+
{
|
| 31135 |
+
"epoch": 5.064957264957265,
|
| 31136 |
+
"grad_norm": 0.18554766476154327,
|
| 31137 |
+
"learning_rate": 4.416009267594657e-05,
|
| 31138 |
+
"loss": 0.7825,
|
| 31139 |
+
"step": 4447
|
| 31140 |
+
},
|
| 31141 |
+
{
|
| 31142 |
+
"epoch": 5.066096866096866,
|
| 31143 |
+
"grad_norm": 0.1563161313533783,
|
| 31144 |
+
"learning_rate": 4.415709947529995e-05,
|
| 31145 |
+
"loss": 0.795,
|
| 31146 |
+
"step": 4448
|
| 31147 |
+
},
|
| 31148 |
+
{
|
| 31149 |
+
"epoch": 5.067236467236468,
|
| 31150 |
+
"grad_norm": 0.14149203896522522,
|
| 31151 |
+
"learning_rate": 4.4154105609274585e-05,
|
| 31152 |
+
"loss": 0.9252,
|
| 31153 |
+
"step": 4449
|
| 31154 |
+
},
|
| 31155 |
+
{
|
| 31156 |
+
"epoch": 5.068376068376068,
|
| 31157 |
+
"grad_norm": 0.16730783879756927,
|
| 31158 |
+
"learning_rate": 4.415111107797445e-05,
|
| 31159 |
+
"loss": 0.6496,
|
| 31160 |
+
"step": 4450
|
| 31161 |
+
},
|
| 31162 |
+
{
|
| 31163 |
+
"epoch": 5.06951566951567,
|
| 31164 |
+
"grad_norm": 0.17725302278995514,
|
| 31165 |
+
"learning_rate": 4.414811588150357e-05,
|
| 31166 |
+
"loss": 0.8285,
|
| 31167 |
+
"step": 4451
|
| 31168 |
+
},
|
| 31169 |
+
{
|
| 31170 |
+
"epoch": 5.070655270655271,
|
| 31171 |
+
"grad_norm": 0.1912432610988617,
|
| 31172 |
+
"learning_rate": 4.414512001996596e-05,
|
| 31173 |
+
"loss": 0.7049,
|
| 31174 |
+
"step": 4452
|
| 31175 |
+
},
|
| 31176 |
+
{
|
| 31177 |
+
"epoch": 5.0717948717948715,
|
| 31178 |
+
"grad_norm": 0.13255245983600616,
|
| 31179 |
+
"learning_rate": 4.414212349346569e-05,
|
| 31180 |
+
"loss": 1.0307,
|
| 31181 |
+
"step": 4453
|
| 31182 |
+
},
|
| 31183 |
+
{
|
| 31184 |
+
"epoch": 5.072934472934473,
|
| 31185 |
+
"grad_norm": 0.18408933281898499,
|
| 31186 |
+
"learning_rate": 4.413912630210683e-05,
|
| 31187 |
+
"loss": 0.7833,
|
| 31188 |
+
"step": 4454
|
| 31189 |
+
},
|
| 31190 |
+
{
|
| 31191 |
+
"epoch": 5.074074074074074,
|
| 31192 |
+
"grad_norm": 0.1737062782049179,
|
| 31193 |
+
"learning_rate": 4.413612844599347e-05,
|
| 31194 |
+
"loss": 0.7166,
|
| 31195 |
+
"step": 4455
|
| 31196 |
+
},
|
| 31197 |
+
{
|
| 31198 |
+
"epoch": 5.075213675213675,
|
| 31199 |
+
"grad_norm": 0.1808139979839325,
|
| 31200 |
+
"learning_rate": 4.4133129925229754e-05,
|
| 31201 |
+
"loss": 0.8399,
|
| 31202 |
+
"step": 4456
|
| 31203 |
+
},
|
| 31204 |
+
{
|
| 31205 |
+
"epoch": 5.076353276353276,
|
| 31206 |
+
"grad_norm": 0.15159174799919128,
|
| 31207 |
+
"learning_rate": 4.413013073991982e-05,
|
| 31208 |
+
"loss": 0.9164,
|
| 31209 |
+
"step": 4457
|
| 31210 |
+
},
|
| 31211 |
+
{
|
| 31212 |
+
"epoch": 5.077492877492878,
|
| 31213 |
+
"grad_norm": 0.1934349536895752,
|
| 31214 |
+
"learning_rate": 4.412713089016783e-05,
|
| 31215 |
+
"loss": 0.7688,
|
| 31216 |
+
"step": 4458
|
| 31217 |
+
},
|
| 31218 |
+
{
|
| 31219 |
+
"epoch": 5.078632478632478,
|
| 31220 |
+
"grad_norm": 0.1845472753047943,
|
| 31221 |
+
"learning_rate": 4.412413037607799e-05,
|
| 31222 |
+
"loss": 0.7111,
|
| 31223 |
+
"step": 4459
|
| 31224 |
+
},
|
| 31225 |
+
{
|
| 31226 |
+
"epoch": 5.07977207977208,
|
| 31227 |
+
"grad_norm": 0.19052857160568237,
|
| 31228 |
+
"learning_rate": 4.4121129197754505e-05,
|
| 31229 |
+
"loss": 0.644,
|
| 31230 |
+
"step": 4460
|
| 31231 |
+
},
|
| 31232 |
+
{
|
| 31233 |
+
"epoch": 5.080911680911681,
|
| 31234 |
+
"grad_norm": 0.1481504887342453,
|
| 31235 |
+
"learning_rate": 4.4118127355301625e-05,
|
| 31236 |
+
"loss": 0.8329,
|
| 31237 |
+
"step": 4461
|
| 31238 |
+
},
|
| 31239 |
+
{
|
| 31240 |
+
"epoch": 5.082051282051282,
|
| 31241 |
+
"grad_norm": 0.16264614462852478,
|
| 31242 |
+
"learning_rate": 4.411512484882361e-05,
|
| 31243 |
+
"loss": 0.7063,
|
| 31244 |
+
"step": 4462
|
| 31245 |
+
},
|
| 31246 |
+
{
|
| 31247 |
+
"epoch": 5.083190883190883,
|
| 31248 |
+
"grad_norm": 0.15884508192539215,
|
| 31249 |
+
"learning_rate": 4.4112121678424735e-05,
|
| 31250 |
+
"loss": 0.9177,
|
| 31251 |
+
"step": 4463
|
| 31252 |
+
},
|
| 31253 |
+
{
|
| 31254 |
+
"epoch": 5.084330484330485,
|
| 31255 |
+
"grad_norm": 0.19420745968818665,
|
| 31256 |
+
"learning_rate": 4.410911784420931e-05,
|
| 31257 |
+
"loss": 0.7955,
|
| 31258 |
+
"step": 4464
|
| 31259 |
+
},
|
| 31260 |
+
{
|
| 31261 |
+
"epoch": 5.085470085470085,
|
| 31262 |
+
"grad_norm": 0.13226862251758575,
|
| 31263 |
+
"learning_rate": 4.410611334628169e-05,
|
| 31264 |
+
"loss": 1.0122,
|
| 31265 |
+
"step": 4465
|
| 31266 |
+
},
|
| 31267 |
+
{
|
| 31268 |
+
"epoch": 5.086609686609687,
|
| 31269 |
+
"grad_norm": 0.19133615493774414,
|
| 31270 |
+
"learning_rate": 4.4103108184746203e-05,
|
| 31271 |
+
"loss": 0.6311,
|
| 31272 |
+
"step": 4466
|
| 31273 |
+
},
|
| 31274 |
+
{
|
| 31275 |
+
"epoch": 5.087749287749288,
|
| 31276 |
+
"grad_norm": 0.19149358570575714,
|
| 31277 |
+
"learning_rate": 4.410010235970723e-05,
|
| 31278 |
+
"loss": 0.7162,
|
| 31279 |
+
"step": 4467
|
| 31280 |
+
},
|
| 31281 |
+
{
|
| 31282 |
+
"epoch": 5.088888888888889,
|
| 31283 |
+
"grad_norm": 0.17075753211975098,
|
| 31284 |
+
"learning_rate": 4.409709587126918e-05,
|
| 31285 |
+
"loss": 0.8938,
|
| 31286 |
+
"step": 4468
|
| 31287 |
+
},
|
| 31288 |
+
{
|
| 31289 |
+
"epoch": 5.09002849002849,
|
| 31290 |
+
"grad_norm": 0.1778605431318283,
|
| 31291 |
+
"learning_rate": 4.409408871953647e-05,
|
| 31292 |
+
"loss": 0.8742,
|
| 31293 |
+
"step": 4469
|
| 31294 |
+
},
|
| 31295 |
+
{
|
| 31296 |
+
"epoch": 5.091168091168091,
|
| 31297 |
+
"grad_norm": 0.14712361991405487,
|
| 31298 |
+
"learning_rate": 4.4091080904613557e-05,
|
| 31299 |
+
"loss": 0.9194,
|
| 31300 |
+
"step": 4470
|
| 31301 |
+
},
|
| 31302 |
+
{
|
| 31303 |
+
"epoch": 5.092307692307692,
|
| 31304 |
+
"grad_norm": 0.18350447714328766,
|
| 31305 |
+
"learning_rate": 4.40880724266049e-05,
|
| 31306 |
+
"loss": 0.7872,
|
| 31307 |
+
"step": 4471
|
| 31308 |
+
},
|
| 31309 |
+
{
|
| 31310 |
+
"epoch": 5.093447293447293,
|
| 31311 |
+
"grad_norm": 0.17689688503742218,
|
| 31312 |
+
"learning_rate": 4.408506328561499e-05,
|
| 31313 |
+
"loss": 0.7369,
|
| 31314 |
+
"step": 4472
|
| 31315 |
+
},
|
| 31316 |
+
{
|
| 31317 |
+
"epoch": 5.094586894586895,
|
| 31318 |
+
"grad_norm": 0.15608465671539307,
|
| 31319 |
+
"learning_rate": 4.4082053481748356e-05,
|
| 31320 |
+
"loss": 0.8439,
|
| 31321 |
+
"step": 4473
|
| 31322 |
+
},
|
| 31323 |
+
{
|
| 31324 |
+
"epoch": 5.095726495726495,
|
| 31325 |
+
"grad_norm": 0.18518562614917755,
|
| 31326 |
+
"learning_rate": 4.407904301510953e-05,
|
| 31327 |
+
"loss": 0.7294,
|
| 31328 |
+
"step": 4474
|
| 31329 |
+
},
|
| 31330 |
+
{
|
| 31331 |
+
"epoch": 5.096866096866097,
|
| 31332 |
+
"grad_norm": 0.1898130178451538,
|
| 31333 |
+
"learning_rate": 4.407603188580306e-05,
|
| 31334 |
+
"loss": 0.7844,
|
| 31335 |
+
"step": 4475
|
| 31336 |
+
},
|
| 31337 |
+
{
|
| 31338 |
+
"epoch": 5.098005698005698,
|
| 31339 |
+
"grad_norm": 0.19604942202568054,
|
| 31340 |
+
"learning_rate": 4.407302009393356e-05,
|
| 31341 |
+
"loss": 0.772,
|
| 31342 |
+
"step": 4476
|
| 31343 |
+
},
|
| 31344 |
+
{
|
| 31345 |
+
"epoch": 5.099145299145299,
|
| 31346 |
+
"grad_norm": 0.166913703083992,
|
| 31347 |
+
"learning_rate": 4.407000763960561e-05,
|
| 31348 |
+
"loss": 0.7377,
|
| 31349 |
+
"step": 4477
|
| 31350 |
+
},
|
| 31351 |
+
{
|
| 31352 |
+
"epoch": 5.1002849002849,
|
| 31353 |
+
"grad_norm": 0.1579706072807312,
|
| 31354 |
+
"learning_rate": 4.4066994522923854e-05,
|
| 31355 |
+
"loss": 0.88,
|
| 31356 |
+
"step": 4478
|
| 31357 |
+
},
|
| 31358 |
+
{
|
| 31359 |
+
"epoch": 5.101424501424502,
|
| 31360 |
+
"grad_norm": 0.14575885236263275,
|
| 31361 |
+
"learning_rate": 4.406398074399294e-05,
|
| 31362 |
+
"loss": 0.7705,
|
| 31363 |
+
"step": 4479
|
| 31364 |
+
},
|
| 31365 |
+
{
|
| 31366 |
+
"epoch": 5.102564102564102,
|
| 31367 |
+
"grad_norm": 0.1716032177209854,
|
| 31368 |
+
"learning_rate": 4.406096630291755e-05,
|
| 31369 |
+
"loss": 0.9158,
|
| 31370 |
+
"step": 4480
|
| 31371 |
+
},
|
| 31372 |
+
{
|
| 31373 |
+
"epoch": 5.103703703703704,
|
| 31374 |
+
"grad_norm": 0.19217745959758759,
|
| 31375 |
+
"learning_rate": 4.40579511998024e-05,
|
| 31376 |
+
"loss": 0.6437,
|
| 31377 |
+
"step": 4481
|
| 31378 |
+
},
|
| 31379 |
+
{
|
| 31380 |
+
"epoch": 5.104843304843305,
|
| 31381 |
+
"grad_norm": 0.1495896875858307,
|
| 31382 |
+
"learning_rate": 4.4054935434752176e-05,
|
| 31383 |
+
"loss": 0.8326,
|
| 31384 |
+
"step": 4482
|
| 31385 |
+
},
|
| 31386 |
+
{
|
| 31387 |
+
"epoch": 5.105982905982906,
|
| 31388 |
+
"grad_norm": 0.17360635101795197,
|
| 31389 |
+
"learning_rate": 4.405191900787164e-05,
|
| 31390 |
+
"loss": 0.7865,
|
| 31391 |
+
"step": 4483
|
| 31392 |
+
},
|
| 31393 |
+
{
|
| 31394 |
+
"epoch": 5.107122507122507,
|
| 31395 |
+
"grad_norm": 0.17083071172237396,
|
| 31396 |
+
"learning_rate": 4.404890191926557e-05,
|
| 31397 |
+
"loss": 0.9054,
|
| 31398 |
+
"step": 4484
|
| 31399 |
+
},
|
| 31400 |
+
{
|
| 31401 |
+
"epoch": 5.1082621082621085,
|
| 31402 |
+
"grad_norm": 0.14887142181396484,
|
| 31403 |
+
"learning_rate": 4.404588416903876e-05,
|
| 31404 |
+
"loss": 0.8747,
|
| 31405 |
+
"step": 4485
|
| 31406 |
+
},
|
| 31407 |
+
{
|
| 31408 |
+
"epoch": 5.109401709401709,
|
| 31409 |
+
"grad_norm": 0.1598469316959381,
|
| 31410 |
+
"learning_rate": 4.4042865757296016e-05,
|
| 31411 |
+
"loss": 0.7279,
|
| 31412 |
+
"step": 4486
|
| 31413 |
+
},
|
| 31414 |
+
{
|
| 31415 |
+
"epoch": 5.1105413105413104,
|
| 31416 |
+
"grad_norm": 0.19548645615577698,
|
| 31417 |
+
"learning_rate": 4.403984668414216e-05,
|
| 31418 |
+
"loss": 0.8635,
|
| 31419 |
+
"step": 4487
|
| 31420 |
+
},
|
| 31421 |
+
{
|
| 31422 |
+
"epoch": 5.111680911680912,
|
| 31423 |
+
"grad_norm": 0.1797143518924713,
|
| 31424 |
+
"learning_rate": 4.403682694968209e-05,
|
| 31425 |
+
"loss": 0.7134,
|
| 31426 |
+
"step": 4488
|
| 31427 |
+
},
|
| 31428 |
+
{
|
| 31429 |
+
"epoch": 5.112820512820512,
|
| 31430 |
+
"grad_norm": 0.1726599931716919,
|
| 31431 |
+
"learning_rate": 4.403380655402065e-05,
|
| 31432 |
+
"loss": 0.7458,
|
| 31433 |
+
"step": 4489
|
| 31434 |
+
},
|
| 31435 |
+
{
|
| 31436 |
+
"epoch": 5.113960113960114,
|
| 31437 |
+
"grad_norm": 0.18311962485313416,
|
| 31438 |
+
"learning_rate": 4.403078549726277e-05,
|
| 31439 |
+
"loss": 0.7293,
|
| 31440 |
+
"step": 4490
|
| 31441 |
+
},
|
| 31442 |
+
{
|
| 31443 |
+
"epoch": 5.115099715099715,
|
| 31444 |
+
"grad_norm": 0.1566498577594757,
|
| 31445 |
+
"learning_rate": 4.4027763779513374e-05,
|
| 31446 |
+
"loss": 0.7851,
|
| 31447 |
+
"step": 4491
|
| 31448 |
+
},
|
| 31449 |
+
{
|
| 31450 |
+
"epoch": 5.116239316239316,
|
| 31451 |
+
"grad_norm": 0.1594432145357132,
|
| 31452 |
+
"learning_rate": 4.402474140087742e-05,
|
| 31453 |
+
"loss": 0.8625,
|
| 31454 |
+
"step": 4492
|
| 31455 |
+
},
|
| 31456 |
+
{
|
| 31457 |
+
"epoch": 5.117378917378917,
|
| 31458 |
+
"grad_norm": 0.18681517243385315,
|
| 31459 |
+
"learning_rate": 4.402171836145989e-05,
|
| 31460 |
+
"loss": 0.7257,
|
| 31461 |
+
"step": 4493
|
| 31462 |
+
},
|
| 31463 |
+
{
|
| 31464 |
+
"epoch": 5.118518518518519,
|
| 31465 |
+
"grad_norm": 0.1775273233652115,
|
| 31466 |
+
"learning_rate": 4.401869466136575e-05,
|
| 31467 |
+
"loss": 0.8234,
|
| 31468 |
+
"step": 4494
|
| 31469 |
+
},
|
| 31470 |
+
{
|
| 31471 |
+
"epoch": 5.119658119658119,
|
| 31472 |
+
"grad_norm": 0.19038119912147522,
|
| 31473 |
+
"learning_rate": 4.4015670300700055e-05,
|
| 31474 |
+
"loss": 0.6557,
|
| 31475 |
+
"step": 4495
|
| 31476 |
+
},
|
| 31477 |
+
{
|
| 31478 |
+
"epoch": 5.120797720797721,
|
| 31479 |
+
"grad_norm": 0.1493513286113739,
|
| 31480 |
+
"learning_rate": 4.4012645279567835e-05,
|
| 31481 |
+
"loss": 0.8501,
|
| 31482 |
+
"step": 4496
|
| 31483 |
+
},
|
| 31484 |
+
{
|
| 31485 |
+
"epoch": 5.121937321937322,
|
| 31486 |
+
"grad_norm": 0.1727079302072525,
|
| 31487 |
+
"learning_rate": 4.400961959807416e-05,
|
| 31488 |
+
"loss": 0.6683,
|
| 31489 |
+
"step": 4497
|
| 31490 |
+
},
|
| 31491 |
+
{
|
| 31492 |
+
"epoch": 5.123076923076923,
|
| 31493 |
+
"grad_norm": 0.19639013707637787,
|
| 31494 |
+
"learning_rate": 4.400659325632411e-05,
|
| 31495 |
+
"loss": 0.6409,
|
| 31496 |
+
"step": 4498
|
| 31497 |
+
},
|
| 31498 |
+
{
|
| 31499 |
+
"epoch": 5.124216524216524,
|
| 31500 |
+
"grad_norm": 0.16199037432670593,
|
| 31501 |
+
"learning_rate": 4.400356625442282e-05,
|
| 31502 |
+
"loss": 0.9381,
|
| 31503 |
+
"step": 4499
|
| 31504 |
+
},
|
| 31505 |
+
{
|
| 31506 |
+
"epoch": 5.1253561253561255,
|
| 31507 |
+
"grad_norm": 0.14642073214054108,
|
| 31508 |
+
"learning_rate": 4.400053859247541e-05,
|
| 31509 |
+
"loss": 0.8541,
|
| 31510 |
+
"step": 4500
|
| 31511 |
}
|
| 31512 |
],
|
| 31513 |
"logging_steps": 1,
|
|
|
|
| 31527 |
"attributes": {}
|
| 31528 |
}
|
| 31529 |
},
|
| 31530 |
+
"total_flos": 2.5160574942544527e+19,
|
| 31531 |
"train_batch_size": 8,
|
| 31532 |
"trial_name": null,
|
| 31533 |
"trial_params": null
|