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 6300, 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 sha256:27f3e0b963de9d947bfd4f1dbb200e725a3bd847fbe4c8c3ecbbbf7ef6865b34
|
| 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:ebd21ad2a95fbfa29dc9210ae93d956985f7dc8730120664e54d0c74904c4446
|
| 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:fdc37bbd2e979f041dfbbb004a5c74bab6cdda159cb18116df728588515a9ef6
|
| 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:fb40a0ac67ba9184235f7ee2c1ddb8e2eb82c69f3fe20017a53d91a21db61877
|
| 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,
|
|
@@ -42008,6 +42008,2106 @@
|
|
| 42008 |
"learning_rate": 3.877986722177158e-05,
|
| 42009 |
"loss": 0.7206,
|
| 42010 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42011 |
}
|
| 42012 |
],
|
| 42013 |
"logging_steps": 1,
|
|
@@ -42027,7 +44127,7 @@
|
|
| 42027 |
"attributes": {}
|
| 42028 |
}
|
| 42029 |
},
|
| 42030 |
-
"total_flos": 3.
|
| 42031 |
"train_batch_size": 8,
|
| 42032 |
"trial_name": null,
|
| 42033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.175498575498575,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 42008 |
"learning_rate": 3.877986722177158e-05,
|
| 42009 |
"loss": 0.7206,
|
| 42010 |
"step": 6000
|
| 42011 |
+
},
|
| 42012 |
+
{
|
| 42013 |
+
"epoch": 6.835327635327635,
|
| 42014 |
+
"grad_norm": 0.18114681541919708,
|
| 42015 |
+
"learning_rate": 3.8775979470484856e-05,
|
| 42016 |
+
"loss": 0.7812,
|
| 42017 |
+
"step": 6001
|
| 42018 |
+
},
|
| 42019 |
+
{
|
| 42020 |
+
"epoch": 6.836467236467237,
|
| 42021 |
+
"grad_norm": 0.1992897242307663,
|
| 42022 |
+
"learning_rate": 3.8772091240720485e-05,
|
| 42023 |
+
"loss": 0.8578,
|
| 42024 |
+
"step": 6002
|
| 42025 |
+
},
|
| 42026 |
+
{
|
| 42027 |
+
"epoch": 6.837606837606837,
|
| 42028 |
+
"grad_norm": 0.17705799639225006,
|
| 42029 |
+
"learning_rate": 3.876820253261351e-05,
|
| 42030 |
+
"loss": 0.7819,
|
| 42031 |
+
"step": 6003
|
| 42032 |
+
},
|
| 42033 |
+
{
|
| 42034 |
+
"epoch": 6.838746438746439,
|
| 42035 |
+
"grad_norm": 0.2017027884721756,
|
| 42036 |
+
"learning_rate": 3.8764313346299e-05,
|
| 42037 |
+
"loss": 0.7741,
|
| 42038 |
+
"step": 6004
|
| 42039 |
+
},
|
| 42040 |
+
{
|
| 42041 |
+
"epoch": 6.83988603988604,
|
| 42042 |
+
"grad_norm": 0.20565707981586456,
|
| 42043 |
+
"learning_rate": 3.876042368191203e-05,
|
| 42044 |
+
"loss": 0.6396,
|
| 42045 |
+
"step": 6005
|
| 42046 |
+
},
|
| 42047 |
+
{
|
| 42048 |
+
"epoch": 6.841025641025641,
|
| 42049 |
+
"grad_norm": 0.19953148066997528,
|
| 42050 |
+
"learning_rate": 3.875653353958771e-05,
|
| 42051 |
+
"loss": 0.5716,
|
| 42052 |
+
"step": 6006
|
| 42053 |
+
},
|
| 42054 |
+
{
|
| 42055 |
+
"epoch": 6.842165242165242,
|
| 42056 |
+
"grad_norm": 0.18805484473705292,
|
| 42057 |
+
"learning_rate": 3.875264291946115e-05,
|
| 42058 |
+
"loss": 0.828,
|
| 42059 |
+
"step": 6007
|
| 42060 |
+
},
|
| 42061 |
+
{
|
| 42062 |
+
"epoch": 6.843304843304844,
|
| 42063 |
+
"grad_norm": 0.1909594088792801,
|
| 42064 |
+
"learning_rate": 3.874875182166748e-05,
|
| 42065 |
+
"loss": 0.7643,
|
| 42066 |
+
"step": 6008
|
| 42067 |
+
},
|
| 42068 |
+
{
|
| 42069 |
+
"epoch": 6.844444444444444,
|
| 42070 |
+
"grad_norm": 0.1765531301498413,
|
| 42071 |
+
"learning_rate": 3.874486024634185e-05,
|
| 42072 |
+
"loss": 0.7989,
|
| 42073 |
+
"step": 6009
|
| 42074 |
+
},
|
| 42075 |
+
{
|
| 42076 |
+
"epoch": 6.8455840455840455,
|
| 42077 |
+
"grad_norm": 0.25546133518218994,
|
| 42078 |
+
"learning_rate": 3.874096819361942e-05,
|
| 42079 |
+
"loss": 0.5542,
|
| 42080 |
+
"step": 6010
|
| 42081 |
+
},
|
| 42082 |
+
{
|
| 42083 |
+
"epoch": 6.846723646723647,
|
| 42084 |
+
"grad_norm": 0.21030516922473907,
|
| 42085 |
+
"learning_rate": 3.873707566363538e-05,
|
| 42086 |
+
"loss": 0.5716,
|
| 42087 |
+
"step": 6011
|
| 42088 |
+
},
|
| 42089 |
+
{
|
| 42090 |
+
"epoch": 6.8478632478632475,
|
| 42091 |
+
"grad_norm": 0.15768931806087494,
|
| 42092 |
+
"learning_rate": 3.873318265652493e-05,
|
| 42093 |
+
"loss": 0.9758,
|
| 42094 |
+
"step": 6012
|
| 42095 |
+
},
|
| 42096 |
+
{
|
| 42097 |
+
"epoch": 6.849002849002849,
|
| 42098 |
+
"grad_norm": 0.24656745791435242,
|
| 42099 |
+
"learning_rate": 3.872928917242328e-05,
|
| 42100 |
+
"loss": 0.7578,
|
| 42101 |
+
"step": 6013
|
| 42102 |
+
},
|
| 42103 |
+
{
|
| 42104 |
+
"epoch": 6.85014245014245,
|
| 42105 |
+
"grad_norm": 0.21918340027332306,
|
| 42106 |
+
"learning_rate": 3.872539521146565e-05,
|
| 42107 |
+
"loss": 0.6557,
|
| 42108 |
+
"step": 6014
|
| 42109 |
+
},
|
| 42110 |
+
{
|
| 42111 |
+
"epoch": 6.851282051282051,
|
| 42112 |
+
"grad_norm": 0.2026132196187973,
|
| 42113 |
+
"learning_rate": 3.872150077378731e-05,
|
| 42114 |
+
"loss": 0.7647,
|
| 42115 |
+
"step": 6015
|
| 42116 |
+
},
|
| 42117 |
+
{
|
| 42118 |
+
"epoch": 6.852421652421652,
|
| 42119 |
+
"grad_norm": 0.20676188170909882,
|
| 42120 |
+
"learning_rate": 3.871760585952351e-05,
|
| 42121 |
+
"loss": 0.6727,
|
| 42122 |
+
"step": 6016
|
| 42123 |
+
},
|
| 42124 |
+
{
|
| 42125 |
+
"epoch": 6.853561253561254,
|
| 42126 |
+
"grad_norm": 0.17937958240509033,
|
| 42127 |
+
"learning_rate": 3.871371046880954e-05,
|
| 42128 |
+
"loss": 0.7444,
|
| 42129 |
+
"step": 6017
|
| 42130 |
+
},
|
| 42131 |
+
{
|
| 42132 |
+
"epoch": 6.854700854700854,
|
| 42133 |
+
"grad_norm": 0.20318861305713654,
|
| 42134 |
+
"learning_rate": 3.870981460178069e-05,
|
| 42135 |
+
"loss": 0.8459,
|
| 42136 |
+
"step": 6018
|
| 42137 |
+
},
|
| 42138 |
+
{
|
| 42139 |
+
"epoch": 6.855840455840456,
|
| 42140 |
+
"grad_norm": 0.16790197789669037,
|
| 42141 |
+
"learning_rate": 3.870591825857227e-05,
|
| 42142 |
+
"loss": 0.7932,
|
| 42143 |
+
"step": 6019
|
| 42144 |
+
},
|
| 42145 |
+
{
|
| 42146 |
+
"epoch": 6.856980056980057,
|
| 42147 |
+
"grad_norm": 0.20463784039020538,
|
| 42148 |
+
"learning_rate": 3.870202143931962e-05,
|
| 42149 |
+
"loss": 0.7491,
|
| 42150 |
+
"step": 6020
|
| 42151 |
+
},
|
| 42152 |
+
{
|
| 42153 |
+
"epoch": 6.858119658119658,
|
| 42154 |
+
"grad_norm": 0.1709291934967041,
|
| 42155 |
+
"learning_rate": 3.8698124144158096e-05,
|
| 42156 |
+
"loss": 0.7971,
|
| 42157 |
+
"step": 6021
|
| 42158 |
+
},
|
| 42159 |
+
{
|
| 42160 |
+
"epoch": 6.859259259259259,
|
| 42161 |
+
"grad_norm": 0.21086876094341278,
|
| 42162 |
+
"learning_rate": 3.869422637322304e-05,
|
| 42163 |
+
"loss": 0.7615,
|
| 42164 |
+
"step": 6022
|
| 42165 |
+
},
|
| 42166 |
+
{
|
| 42167 |
+
"epoch": 6.860398860398861,
|
| 42168 |
+
"grad_norm": 0.16039279103279114,
|
| 42169 |
+
"learning_rate": 3.8690328126649845e-05,
|
| 42170 |
+
"loss": 0.7821,
|
| 42171 |
+
"step": 6023
|
| 42172 |
+
},
|
| 42173 |
+
{
|
| 42174 |
+
"epoch": 6.861538461538462,
|
| 42175 |
+
"grad_norm": 0.17380090057849884,
|
| 42176 |
+
"learning_rate": 3.8686429404573905e-05,
|
| 42177 |
+
"loss": 0.8232,
|
| 42178 |
+
"step": 6024
|
| 42179 |
+
},
|
| 42180 |
+
{
|
| 42181 |
+
"epoch": 6.862678062678063,
|
| 42182 |
+
"grad_norm": 0.18670782446861267,
|
| 42183 |
+
"learning_rate": 3.868253020713063e-05,
|
| 42184 |
+
"loss": 0.6692,
|
| 42185 |
+
"step": 6025
|
| 42186 |
+
},
|
| 42187 |
+
{
|
| 42188 |
+
"epoch": 6.863817663817664,
|
| 42189 |
+
"grad_norm": 0.16718174517154694,
|
| 42190 |
+
"learning_rate": 3.867863053445546e-05,
|
| 42191 |
+
"loss": 0.8576,
|
| 42192 |
+
"step": 6026
|
| 42193 |
+
},
|
| 42194 |
+
{
|
| 42195 |
+
"epoch": 6.864957264957265,
|
| 42196 |
+
"grad_norm": 0.1585511863231659,
|
| 42197 |
+
"learning_rate": 3.8674730386683835e-05,
|
| 42198 |
+
"loss": 0.7946,
|
| 42199 |
+
"step": 6027
|
| 42200 |
+
},
|
| 42201 |
+
{
|
| 42202 |
+
"epoch": 6.866096866096866,
|
| 42203 |
+
"grad_norm": 0.190469428896904,
|
| 42204 |
+
"learning_rate": 3.8670829763951214e-05,
|
| 42205 |
+
"loss": 0.7718,
|
| 42206 |
+
"step": 6028
|
| 42207 |
+
},
|
| 42208 |
+
{
|
| 42209 |
+
"epoch": 6.867236467236467,
|
| 42210 |
+
"grad_norm": 0.19864922761917114,
|
| 42211 |
+
"learning_rate": 3.8666928666393085e-05,
|
| 42212 |
+
"loss": 0.6731,
|
| 42213 |
+
"step": 6029
|
| 42214 |
+
},
|
| 42215 |
+
{
|
| 42216 |
+
"epoch": 6.868376068376069,
|
| 42217 |
+
"grad_norm": 0.22138063609600067,
|
| 42218 |
+
"learning_rate": 3.866302709414494e-05,
|
| 42219 |
+
"loss": 0.6512,
|
| 42220 |
+
"step": 6030
|
| 42221 |
+
},
|
| 42222 |
+
{
|
| 42223 |
+
"epoch": 6.869515669515669,
|
| 42224 |
+
"grad_norm": 0.22428637742996216,
|
| 42225 |
+
"learning_rate": 3.865912504734228e-05,
|
| 42226 |
+
"loss": 0.5032,
|
| 42227 |
+
"step": 6031
|
| 42228 |
+
},
|
| 42229 |
+
{
|
| 42230 |
+
"epoch": 6.870655270655271,
|
| 42231 |
+
"grad_norm": 0.17769813537597656,
|
| 42232 |
+
"learning_rate": 3.8655222526120647e-05,
|
| 42233 |
+
"loss": 0.8244,
|
| 42234 |
+
"step": 6032
|
| 42235 |
+
},
|
| 42236 |
+
{
|
| 42237 |
+
"epoch": 6.871794871794872,
|
| 42238 |
+
"grad_norm": 0.18228816986083984,
|
| 42239 |
+
"learning_rate": 3.865131953061559e-05,
|
| 42240 |
+
"loss": 0.7863,
|
| 42241 |
+
"step": 6033
|
| 42242 |
+
},
|
| 42243 |
+
{
|
| 42244 |
+
"epoch": 6.872934472934473,
|
| 42245 |
+
"grad_norm": 0.16256453096866608,
|
| 42246 |
+
"learning_rate": 3.864741606096267e-05,
|
| 42247 |
+
"loss": 0.784,
|
| 42248 |
+
"step": 6034
|
| 42249 |
+
},
|
| 42250 |
+
{
|
| 42251 |
+
"epoch": 6.874074074074074,
|
| 42252 |
+
"grad_norm": 0.20455239713191986,
|
| 42253 |
+
"learning_rate": 3.864351211729745e-05,
|
| 42254 |
+
"loss": 0.8365,
|
| 42255 |
+
"step": 6035
|
| 42256 |
+
},
|
| 42257 |
+
{
|
| 42258 |
+
"epoch": 6.875213675213676,
|
| 42259 |
+
"grad_norm": 0.2072412371635437,
|
| 42260 |
+
"learning_rate": 3.863960769975554e-05,
|
| 42261 |
+
"loss": 0.7205,
|
| 42262 |
+
"step": 6036
|
| 42263 |
+
},
|
| 42264 |
+
{
|
| 42265 |
+
"epoch": 6.876353276353276,
|
| 42266 |
+
"grad_norm": 0.15931065380573273,
|
| 42267 |
+
"learning_rate": 3.8635702808472544e-05,
|
| 42268 |
+
"loss": 0.9042,
|
| 42269 |
+
"step": 6037
|
| 42270 |
+
},
|
| 42271 |
+
{
|
| 42272 |
+
"epoch": 6.877492877492878,
|
| 42273 |
+
"grad_norm": 0.15490956604480743,
|
| 42274 |
+
"learning_rate": 3.8631797443584084e-05,
|
| 42275 |
+
"loss": 0.8965,
|
| 42276 |
+
"step": 6038
|
| 42277 |
+
},
|
| 42278 |
+
{
|
| 42279 |
+
"epoch": 6.878632478632479,
|
| 42280 |
+
"grad_norm": 0.208894744515419,
|
| 42281 |
+
"learning_rate": 3.862789160522582e-05,
|
| 42282 |
+
"loss": 0.6424,
|
| 42283 |
+
"step": 6039
|
| 42284 |
+
},
|
| 42285 |
+
{
|
| 42286 |
+
"epoch": 6.87977207977208,
|
| 42287 |
+
"grad_norm": 0.20632405579090118,
|
| 42288 |
+
"learning_rate": 3.862398529353341e-05,
|
| 42289 |
+
"loss": 0.7237,
|
| 42290 |
+
"step": 6040
|
| 42291 |
+
},
|
| 42292 |
+
{
|
| 42293 |
+
"epoch": 6.880911680911681,
|
| 42294 |
+
"grad_norm": 0.16035480797290802,
|
| 42295 |
+
"learning_rate": 3.862007850864251e-05,
|
| 42296 |
+
"loss": 0.8734,
|
| 42297 |
+
"step": 6041
|
| 42298 |
+
},
|
| 42299 |
+
{
|
| 42300 |
+
"epoch": 6.8820512820512825,
|
| 42301 |
+
"grad_norm": 0.17163221538066864,
|
| 42302 |
+
"learning_rate": 3.8616171250688825e-05,
|
| 42303 |
+
"loss": 0.8483,
|
| 42304 |
+
"step": 6042
|
| 42305 |
+
},
|
| 42306 |
+
{
|
| 42307 |
+
"epoch": 6.883190883190883,
|
| 42308 |
+
"grad_norm": 0.18672995269298553,
|
| 42309 |
+
"learning_rate": 3.8612263519808075e-05,
|
| 42310 |
+
"loss": 0.7181,
|
| 42311 |
+
"step": 6043
|
| 42312 |
+
},
|
| 42313 |
+
{
|
| 42314 |
+
"epoch": 6.8843304843304844,
|
| 42315 |
+
"grad_norm": 0.16936668753623962,
|
| 42316 |
+
"learning_rate": 3.860835531613598e-05,
|
| 42317 |
+
"loss": 0.7153,
|
| 42318 |
+
"step": 6044
|
| 42319 |
+
},
|
| 42320 |
+
{
|
| 42321 |
+
"epoch": 6.885470085470086,
|
| 42322 |
+
"grad_norm": 0.18464472889900208,
|
| 42323 |
+
"learning_rate": 3.860444663980829e-05,
|
| 42324 |
+
"loss": 0.7194,
|
| 42325 |
+
"step": 6045
|
| 42326 |
+
},
|
| 42327 |
+
{
|
| 42328 |
+
"epoch": 6.886609686609686,
|
| 42329 |
+
"grad_norm": 0.1461935192346573,
|
| 42330 |
+
"learning_rate": 3.860053749096074e-05,
|
| 42331 |
+
"loss": 0.9748,
|
| 42332 |
+
"step": 6046
|
| 42333 |
+
},
|
| 42334 |
+
{
|
| 42335 |
+
"epoch": 6.887749287749288,
|
| 42336 |
+
"grad_norm": 0.2069118469953537,
|
| 42337 |
+
"learning_rate": 3.859662786972913e-05,
|
| 42338 |
+
"loss": 0.6863,
|
| 42339 |
+
"step": 6047
|
| 42340 |
+
},
|
| 42341 |
+
{
|
| 42342 |
+
"epoch": 6.888888888888889,
|
| 42343 |
+
"grad_norm": 0.15878000855445862,
|
| 42344 |
+
"learning_rate": 3.8592717776249244e-05,
|
| 42345 |
+
"loss": 0.6677,
|
| 42346 |
+
"step": 6048
|
| 42347 |
+
},
|
| 42348 |
+
{
|
| 42349 |
+
"epoch": 6.89002849002849,
|
| 42350 |
+
"grad_norm": 0.15306872129440308,
|
| 42351 |
+
"learning_rate": 3.858880721065689e-05,
|
| 42352 |
+
"loss": 0.8074,
|
| 42353 |
+
"step": 6049
|
| 42354 |
+
},
|
| 42355 |
+
{
|
| 42356 |
+
"epoch": 6.891168091168091,
|
| 42357 |
+
"grad_norm": 0.1978970170021057,
|
| 42358 |
+
"learning_rate": 3.858489617308789e-05,
|
| 42359 |
+
"loss": 0.7025,
|
| 42360 |
+
"step": 6050
|
| 42361 |
+
},
|
| 42362 |
+
{
|
| 42363 |
+
"epoch": 6.892307692307693,
|
| 42364 |
+
"grad_norm": 0.17932195961475372,
|
| 42365 |
+
"learning_rate": 3.858098466367809e-05,
|
| 42366 |
+
"loss": 0.8567,
|
| 42367 |
+
"step": 6051
|
| 42368 |
+
},
|
| 42369 |
+
{
|
| 42370 |
+
"epoch": 6.893447293447293,
|
| 42371 |
+
"grad_norm": 0.16375882923603058,
|
| 42372 |
+
"learning_rate": 3.857707268256334e-05,
|
| 42373 |
+
"loss": 0.7409,
|
| 42374 |
+
"step": 6052
|
| 42375 |
+
},
|
| 42376 |
+
{
|
| 42377 |
+
"epoch": 6.894586894586895,
|
| 42378 |
+
"grad_norm": 0.19845464825630188,
|
| 42379 |
+
"learning_rate": 3.857316022987952e-05,
|
| 42380 |
+
"loss": 0.6167,
|
| 42381 |
+
"step": 6053
|
| 42382 |
+
},
|
| 42383 |
+
{
|
| 42384 |
+
"epoch": 6.895726495726496,
|
| 42385 |
+
"grad_norm": 0.1802733838558197,
|
| 42386 |
+
"learning_rate": 3.8569247305762514e-05,
|
| 42387 |
+
"loss": 0.7946,
|
| 42388 |
+
"step": 6054
|
| 42389 |
+
},
|
| 42390 |
+
{
|
| 42391 |
+
"epoch": 6.896866096866097,
|
| 42392 |
+
"grad_norm": 0.19858969748020172,
|
| 42393 |
+
"learning_rate": 3.8565333910348245e-05,
|
| 42394 |
+
"loss": 0.734,
|
| 42395 |
+
"step": 6055
|
| 42396 |
+
},
|
| 42397 |
+
{
|
| 42398 |
+
"epoch": 6.898005698005698,
|
| 42399 |
+
"grad_norm": 0.19176946580410004,
|
| 42400 |
+
"learning_rate": 3.856142004377262e-05,
|
| 42401 |
+
"loss": 0.7769,
|
| 42402 |
+
"step": 6056
|
| 42403 |
+
},
|
| 42404 |
+
{
|
| 42405 |
+
"epoch": 6.8991452991452995,
|
| 42406 |
+
"grad_norm": 0.18545280396938324,
|
| 42407 |
+
"learning_rate": 3.855750570617158e-05,
|
| 42408 |
+
"loss": 0.6867,
|
| 42409 |
+
"step": 6057
|
| 42410 |
+
},
|
| 42411 |
+
{
|
| 42412 |
+
"epoch": 6.9002849002849,
|
| 42413 |
+
"grad_norm": 0.24399203062057495,
|
| 42414 |
+
"learning_rate": 3.855359089768108e-05,
|
| 42415 |
+
"loss": 0.9097,
|
| 42416 |
+
"step": 6058
|
| 42417 |
+
},
|
| 42418 |
+
{
|
| 42419 |
+
"epoch": 6.9014245014245015,
|
| 42420 |
+
"grad_norm": 0.17382477223873138,
|
| 42421 |
+
"learning_rate": 3.85496756184371e-05,
|
| 42422 |
+
"loss": 0.7393,
|
| 42423 |
+
"step": 6059
|
| 42424 |
+
},
|
| 42425 |
+
{
|
| 42426 |
+
"epoch": 6.902564102564103,
|
| 42427 |
+
"grad_norm": 0.1953514963388443,
|
| 42428 |
+
"learning_rate": 3.8545759868575625e-05,
|
| 42429 |
+
"loss": 0.6214,
|
| 42430 |
+
"step": 6060
|
| 42431 |
+
},
|
| 42432 |
+
{
|
| 42433 |
+
"epoch": 6.9037037037037035,
|
| 42434 |
+
"grad_norm": 0.14534224569797516,
|
| 42435 |
+
"learning_rate": 3.8541843648232656e-05,
|
| 42436 |
+
"loss": 0.9603,
|
| 42437 |
+
"step": 6061
|
| 42438 |
+
},
|
| 42439 |
+
{
|
| 42440 |
+
"epoch": 6.904843304843305,
|
| 42441 |
+
"grad_norm": 0.21155428886413574,
|
| 42442 |
+
"learning_rate": 3.8537926957544225e-05,
|
| 42443 |
+
"loss": 0.6902,
|
| 42444 |
+
"step": 6062
|
| 42445 |
+
},
|
| 42446 |
+
{
|
| 42447 |
+
"epoch": 6.905982905982906,
|
| 42448 |
+
"grad_norm": 0.2420935034751892,
|
| 42449 |
+
"learning_rate": 3.853400979664635e-05,
|
| 42450 |
+
"loss": 0.5605,
|
| 42451 |
+
"step": 6063
|
| 42452 |
+
},
|
| 42453 |
+
{
|
| 42454 |
+
"epoch": 6.907122507122507,
|
| 42455 |
+
"grad_norm": 0.20479215681552887,
|
| 42456 |
+
"learning_rate": 3.85300921656751e-05,
|
| 42457 |
+
"loss": 0.6898,
|
| 42458 |
+
"step": 6064
|
| 42459 |
+
},
|
| 42460 |
+
{
|
| 42461 |
+
"epoch": 6.908262108262108,
|
| 42462 |
+
"grad_norm": 0.15989598631858826,
|
| 42463 |
+
"learning_rate": 3.852617406476654e-05,
|
| 42464 |
+
"loss": 0.836,
|
| 42465 |
+
"step": 6065
|
| 42466 |
+
},
|
| 42467 |
+
{
|
| 42468 |
+
"epoch": 6.90940170940171,
|
| 42469 |
+
"grad_norm": 0.18351493775844574,
|
| 42470 |
+
"learning_rate": 3.852225549405677e-05,
|
| 42471 |
+
"loss": 0.6975,
|
| 42472 |
+
"step": 6066
|
| 42473 |
+
},
|
| 42474 |
+
{
|
| 42475 |
+
"epoch": 6.91054131054131,
|
| 42476 |
+
"grad_norm": 0.20182476937770844,
|
| 42477 |
+
"learning_rate": 3.851833645368187e-05,
|
| 42478 |
+
"loss": 0.7256,
|
| 42479 |
+
"step": 6067
|
| 42480 |
+
},
|
| 42481 |
+
{
|
| 42482 |
+
"epoch": 6.911680911680912,
|
| 42483 |
+
"grad_norm": 0.19139719009399414,
|
| 42484 |
+
"learning_rate": 3.851441694377796e-05,
|
| 42485 |
+
"loss": 0.7843,
|
| 42486 |
+
"step": 6068
|
| 42487 |
+
},
|
| 42488 |
+
{
|
| 42489 |
+
"epoch": 6.912820512820513,
|
| 42490 |
+
"grad_norm": 0.1669207364320755,
|
| 42491 |
+
"learning_rate": 3.85104969644812e-05,
|
| 42492 |
+
"loss": 0.7148,
|
| 42493 |
+
"step": 6069
|
| 42494 |
+
},
|
| 42495 |
+
{
|
| 42496 |
+
"epoch": 6.913960113960114,
|
| 42497 |
+
"grad_norm": 0.17730924487113953,
|
| 42498 |
+
"learning_rate": 3.8506576515927717e-05,
|
| 42499 |
+
"loss": 0.8612,
|
| 42500 |
+
"step": 6070
|
| 42501 |
+
},
|
| 42502 |
+
{
|
| 42503 |
+
"epoch": 6.915099715099715,
|
| 42504 |
+
"grad_norm": 0.16904395818710327,
|
| 42505 |
+
"learning_rate": 3.85026555982537e-05,
|
| 42506 |
+
"loss": 0.7853,
|
| 42507 |
+
"step": 6071
|
| 42508 |
+
},
|
| 42509 |
+
{
|
| 42510 |
+
"epoch": 6.9162393162393165,
|
| 42511 |
+
"grad_norm": 0.2015823870897293,
|
| 42512 |
+
"learning_rate": 3.849873421159531e-05,
|
| 42513 |
+
"loss": 0.6923,
|
| 42514 |
+
"step": 6072
|
| 42515 |
+
},
|
| 42516 |
+
{
|
| 42517 |
+
"epoch": 6.917378917378917,
|
| 42518 |
+
"grad_norm": 0.16778279840946198,
|
| 42519 |
+
"learning_rate": 3.849481235608877e-05,
|
| 42520 |
+
"loss": 0.9067,
|
| 42521 |
+
"step": 6073
|
| 42522 |
+
},
|
| 42523 |
+
{
|
| 42524 |
+
"epoch": 6.9185185185185185,
|
| 42525 |
+
"grad_norm": 0.16917239129543304,
|
| 42526 |
+
"learning_rate": 3.849089003187027e-05,
|
| 42527 |
+
"loss": 0.8165,
|
| 42528 |
+
"step": 6074
|
| 42529 |
+
},
|
| 42530 |
+
{
|
| 42531 |
+
"epoch": 6.91965811965812,
|
| 42532 |
+
"grad_norm": 0.23813937604427338,
|
| 42533 |
+
"learning_rate": 3.8486967239076075e-05,
|
| 42534 |
+
"loss": 0.5043,
|
| 42535 |
+
"step": 6075
|
| 42536 |
+
},
|
| 42537 |
+
{
|
| 42538 |
+
"epoch": 6.9207977207977205,
|
| 42539 |
+
"grad_norm": 0.24754557013511658,
|
| 42540 |
+
"learning_rate": 3.8483043977842415e-05,
|
| 42541 |
+
"loss": 0.5972,
|
| 42542 |
+
"step": 6076
|
| 42543 |
+
},
|
| 42544 |
+
{
|
| 42545 |
+
"epoch": 6.921937321937322,
|
| 42546 |
+
"grad_norm": 0.5422152876853943,
|
| 42547 |
+
"learning_rate": 3.847912024830556e-05,
|
| 42548 |
+
"loss": 0.9602,
|
| 42549 |
+
"step": 6077
|
| 42550 |
+
},
|
| 42551 |
+
{
|
| 42552 |
+
"epoch": 6.923076923076923,
|
| 42553 |
+
"grad_norm": 0.19803474843502045,
|
| 42554 |
+
"learning_rate": 3.847519605060178e-05,
|
| 42555 |
+
"loss": 0.6874,
|
| 42556 |
+
"step": 6078
|
| 42557 |
+
},
|
| 42558 |
+
{
|
| 42559 |
+
"epoch": 6.924216524216524,
|
| 42560 |
+
"grad_norm": 0.19350609183311462,
|
| 42561 |
+
"learning_rate": 3.847127138486739e-05,
|
| 42562 |
+
"loss": 0.8061,
|
| 42563 |
+
"step": 6079
|
| 42564 |
+
},
|
| 42565 |
+
{
|
| 42566 |
+
"epoch": 6.925356125356125,
|
| 42567 |
+
"grad_norm": 0.20874303579330444,
|
| 42568 |
+
"learning_rate": 3.846734625123871e-05,
|
| 42569 |
+
"loss": 0.6525,
|
| 42570 |
+
"step": 6080
|
| 42571 |
+
},
|
| 42572 |
+
{
|
| 42573 |
+
"epoch": 6.926495726495727,
|
| 42574 |
+
"grad_norm": 0.1934829205274582,
|
| 42575 |
+
"learning_rate": 3.846342064985204e-05,
|
| 42576 |
+
"loss": 0.8948,
|
| 42577 |
+
"step": 6081
|
| 42578 |
+
},
|
| 42579 |
+
{
|
| 42580 |
+
"epoch": 6.927635327635327,
|
| 42581 |
+
"grad_norm": 0.2268676608800888,
|
| 42582 |
+
"learning_rate": 3.845949458084376e-05,
|
| 42583 |
+
"loss": 0.6561,
|
| 42584 |
+
"step": 6082
|
| 42585 |
+
},
|
| 42586 |
+
{
|
| 42587 |
+
"epoch": 6.928774928774929,
|
| 42588 |
+
"grad_norm": 0.19096451997756958,
|
| 42589 |
+
"learning_rate": 3.845556804435021e-05,
|
| 42590 |
+
"loss": 0.7082,
|
| 42591 |
+
"step": 6083
|
| 42592 |
+
},
|
| 42593 |
+
{
|
| 42594 |
+
"epoch": 6.92991452991453,
|
| 42595 |
+
"grad_norm": 0.2186242789030075,
|
| 42596 |
+
"learning_rate": 3.8451641040507794e-05,
|
| 42597 |
+
"loss": 0.5949,
|
| 42598 |
+
"step": 6084
|
| 42599 |
+
},
|
| 42600 |
+
{
|
| 42601 |
+
"epoch": 6.931054131054131,
|
| 42602 |
+
"grad_norm": 0.1837964653968811,
|
| 42603 |
+
"learning_rate": 3.844771356945287e-05,
|
| 42604 |
+
"loss": 0.7762,
|
| 42605 |
+
"step": 6085
|
| 42606 |
+
},
|
| 42607 |
+
{
|
| 42608 |
+
"epoch": 6.932193732193732,
|
| 42609 |
+
"grad_norm": 0.19915224611759186,
|
| 42610 |
+
"learning_rate": 3.844378563132189e-05,
|
| 42611 |
+
"loss": 0.8012,
|
| 42612 |
+
"step": 6086
|
| 42613 |
+
},
|
| 42614 |
+
{
|
| 42615 |
+
"epoch": 6.933333333333334,
|
| 42616 |
+
"grad_norm": 0.19100026786327362,
|
| 42617 |
+
"learning_rate": 3.8439857226251255e-05,
|
| 42618 |
+
"loss": 0.7764,
|
| 42619 |
+
"step": 6087
|
| 42620 |
+
},
|
| 42621 |
+
{
|
| 42622 |
+
"epoch": 6.934472934472934,
|
| 42623 |
+
"grad_norm": 0.15966521203517914,
|
| 42624 |
+
"learning_rate": 3.843592835437743e-05,
|
| 42625 |
+
"loss": 0.7474,
|
| 42626 |
+
"step": 6088
|
| 42627 |
+
},
|
| 42628 |
+
{
|
| 42629 |
+
"epoch": 6.9356125356125355,
|
| 42630 |
+
"grad_norm": 0.17729613184928894,
|
| 42631 |
+
"learning_rate": 3.843199901583685e-05,
|
| 42632 |
+
"loss": 0.7772,
|
| 42633 |
+
"step": 6089
|
| 42634 |
+
},
|
| 42635 |
+
{
|
| 42636 |
+
"epoch": 6.936752136752137,
|
| 42637 |
+
"grad_norm": 0.21062202751636505,
|
| 42638 |
+
"learning_rate": 3.8428069210766016e-05,
|
| 42639 |
+
"loss": 0.7281,
|
| 42640 |
+
"step": 6090
|
| 42641 |
+
},
|
| 42642 |
+
{
|
| 42643 |
+
"epoch": 6.9378917378917375,
|
| 42644 |
+
"grad_norm": 0.1801566630601883,
|
| 42645 |
+
"learning_rate": 3.842413893930141e-05,
|
| 42646 |
+
"loss": 0.7834,
|
| 42647 |
+
"step": 6091
|
| 42648 |
+
},
|
| 42649 |
+
{
|
| 42650 |
+
"epoch": 6.939031339031339,
|
| 42651 |
+
"grad_norm": 0.19413518905639648,
|
| 42652 |
+
"learning_rate": 3.842020820157954e-05,
|
| 42653 |
+
"loss": 0.9733,
|
| 42654 |
+
"step": 6092
|
| 42655 |
+
},
|
| 42656 |
+
{
|
| 42657 |
+
"epoch": 6.94017094017094,
|
| 42658 |
+
"grad_norm": 0.21270233392715454,
|
| 42659 |
+
"learning_rate": 3.8416276997736935e-05,
|
| 42660 |
+
"loss": 0.6284,
|
| 42661 |
+
"step": 6093
|
| 42662 |
+
},
|
| 42663 |
+
{
|
| 42664 |
+
"epoch": 6.941310541310541,
|
| 42665 |
+
"grad_norm": 0.25936126708984375,
|
| 42666 |
+
"learning_rate": 3.841234532791013e-05,
|
| 42667 |
+
"loss": 0.65,
|
| 42668 |
+
"step": 6094
|
| 42669 |
+
},
|
| 42670 |
+
{
|
| 42671 |
+
"epoch": 6.942450142450142,
|
| 42672 |
+
"grad_norm": 0.14870886504650116,
|
| 42673 |
+
"learning_rate": 3.84084131922357e-05,
|
| 42674 |
+
"loss": 0.9136,
|
| 42675 |
+
"step": 6095
|
| 42676 |
+
},
|
| 42677 |
+
{
|
| 42678 |
+
"epoch": 6.943589743589744,
|
| 42679 |
+
"grad_norm": 0.2110133320093155,
|
| 42680 |
+
"learning_rate": 3.84044805908502e-05,
|
| 42681 |
+
"loss": 0.7237,
|
| 42682 |
+
"step": 6096
|
| 42683 |
+
},
|
| 42684 |
+
{
|
| 42685 |
+
"epoch": 6.944729344729344,
|
| 42686 |
+
"grad_norm": 0.17981089651584625,
|
| 42687 |
+
"learning_rate": 3.840054752389022e-05,
|
| 42688 |
+
"loss": 0.8673,
|
| 42689 |
+
"step": 6097
|
| 42690 |
+
},
|
| 42691 |
+
{
|
| 42692 |
+
"epoch": 6.945868945868946,
|
| 42693 |
+
"grad_norm": 0.21633680164813995,
|
| 42694 |
+
"learning_rate": 3.839661399149237e-05,
|
| 42695 |
+
"loss": 0.6492,
|
| 42696 |
+
"step": 6098
|
| 42697 |
+
},
|
| 42698 |
+
{
|
| 42699 |
+
"epoch": 6.947008547008547,
|
| 42700 |
+
"grad_norm": 0.1665615737438202,
|
| 42701 |
+
"learning_rate": 3.839267999379329e-05,
|
| 42702 |
+
"loss": 0.7253,
|
| 42703 |
+
"step": 6099
|
| 42704 |
+
},
|
| 42705 |
+
{
|
| 42706 |
+
"epoch": 6.948148148148148,
|
| 42707 |
+
"grad_norm": 0.16829712688922882,
|
| 42708 |
+
"learning_rate": 3.838874553092959e-05,
|
| 42709 |
+
"loss": 0.9606,
|
| 42710 |
+
"step": 6100
|
| 42711 |
+
},
|
| 42712 |
+
{
|
| 42713 |
+
"epoch": 6.949287749287749,
|
| 42714 |
+
"grad_norm": 0.2334202229976654,
|
| 42715 |
+
"learning_rate": 3.838481060303795e-05,
|
| 42716 |
+
"loss": 0.6407,
|
| 42717 |
+
"step": 6101
|
| 42718 |
+
},
|
| 42719 |
+
{
|
| 42720 |
+
"epoch": 6.950427350427351,
|
| 42721 |
+
"grad_norm": 0.17394769191741943,
|
| 42722 |
+
"learning_rate": 3.8380875210255026e-05,
|
| 42723 |
+
"loss": 0.7099,
|
| 42724 |
+
"step": 6102
|
| 42725 |
+
},
|
| 42726 |
+
{
|
| 42727 |
+
"epoch": 6.951566951566951,
|
| 42728 |
+
"grad_norm": 0.15774554014205933,
|
| 42729 |
+
"learning_rate": 3.8376939352717504e-05,
|
| 42730 |
+
"loss": 1.03,
|
| 42731 |
+
"step": 6103
|
| 42732 |
+
},
|
| 42733 |
+
{
|
| 42734 |
+
"epoch": 6.952706552706553,
|
| 42735 |
+
"grad_norm": 0.21563377976417542,
|
| 42736 |
+
"learning_rate": 3.8373003030562096e-05,
|
| 42737 |
+
"loss": 0.5559,
|
| 42738 |
+
"step": 6104
|
| 42739 |
+
},
|
| 42740 |
+
{
|
| 42741 |
+
"epoch": 6.953846153846154,
|
| 42742 |
+
"grad_norm": 0.15935485064983368,
|
| 42743 |
+
"learning_rate": 3.836906624392552e-05,
|
| 42744 |
+
"loss": 0.949,
|
| 42745 |
+
"step": 6105
|
| 42746 |
+
},
|
| 42747 |
+
{
|
| 42748 |
+
"epoch": 6.9549857549857546,
|
| 42749 |
+
"grad_norm": 0.18906600773334503,
|
| 42750 |
+
"learning_rate": 3.8365128992944496e-05,
|
| 42751 |
+
"loss": 0.6684,
|
| 42752 |
+
"step": 6106
|
| 42753 |
+
},
|
| 42754 |
+
{
|
| 42755 |
+
"epoch": 6.956125356125356,
|
| 42756 |
+
"grad_norm": 0.19462430477142334,
|
| 42757 |
+
"learning_rate": 3.83611912777558e-05,
|
| 42758 |
+
"loss": 0.7422,
|
| 42759 |
+
"step": 6107
|
| 42760 |
+
},
|
| 42761 |
+
{
|
| 42762 |
+
"epoch": 6.957264957264957,
|
| 42763 |
+
"grad_norm": 0.16680681705474854,
|
| 42764 |
+
"learning_rate": 3.835725309849618e-05,
|
| 42765 |
+
"loss": 0.9508,
|
| 42766 |
+
"step": 6108
|
| 42767 |
+
},
|
| 42768 |
+
{
|
| 42769 |
+
"epoch": 6.958404558404558,
|
| 42770 |
+
"grad_norm": 0.20158030092716217,
|
| 42771 |
+
"learning_rate": 3.835331445530243e-05,
|
| 42772 |
+
"loss": 0.7641,
|
| 42773 |
+
"step": 6109
|
| 42774 |
+
},
|
| 42775 |
+
{
|
| 42776 |
+
"epoch": 6.959544159544159,
|
| 42777 |
+
"grad_norm": 0.165785014629364,
|
| 42778 |
+
"learning_rate": 3.834937534831135e-05,
|
| 42779 |
+
"loss": 1.009,
|
| 42780 |
+
"step": 6110
|
| 42781 |
+
},
|
| 42782 |
+
{
|
| 42783 |
+
"epoch": 6.960683760683761,
|
| 42784 |
+
"grad_norm": 0.260774701833725,
|
| 42785 |
+
"learning_rate": 3.834543577765975e-05,
|
| 42786 |
+
"loss": 0.5141,
|
| 42787 |
+
"step": 6111
|
| 42788 |
+
},
|
| 42789 |
+
{
|
| 42790 |
+
"epoch": 6.961823361823361,
|
| 42791 |
+
"grad_norm": 0.20132353901863098,
|
| 42792 |
+
"learning_rate": 3.834149574348447e-05,
|
| 42793 |
+
"loss": 0.7545,
|
| 42794 |
+
"step": 6112
|
| 42795 |
+
},
|
| 42796 |
+
{
|
| 42797 |
+
"epoch": 6.962962962962963,
|
| 42798 |
+
"grad_norm": 0.18978120386600494,
|
| 42799 |
+
"learning_rate": 3.833755524592235e-05,
|
| 42800 |
+
"loss": 0.7082,
|
| 42801 |
+
"step": 6113
|
| 42802 |
+
},
|
| 42803 |
+
{
|
| 42804 |
+
"epoch": 6.964102564102564,
|
| 42805 |
+
"grad_norm": 0.19258476793766022,
|
| 42806 |
+
"learning_rate": 3.833361428511026e-05,
|
| 42807 |
+
"loss": 0.8663,
|
| 42808 |
+
"step": 6114
|
| 42809 |
+
},
|
| 42810 |
+
{
|
| 42811 |
+
"epoch": 6.965242165242165,
|
| 42812 |
+
"grad_norm": 0.19694635272026062,
|
| 42813 |
+
"learning_rate": 3.832967286118507e-05,
|
| 42814 |
+
"loss": 0.8062,
|
| 42815 |
+
"step": 6115
|
| 42816 |
+
},
|
| 42817 |
+
{
|
| 42818 |
+
"epoch": 6.966381766381766,
|
| 42819 |
+
"grad_norm": 0.17284518480300903,
|
| 42820 |
+
"learning_rate": 3.832573097428369e-05,
|
| 42821 |
+
"loss": 0.6405,
|
| 42822 |
+
"step": 6116
|
| 42823 |
+
},
|
| 42824 |
+
{
|
| 42825 |
+
"epoch": 6.967521367521368,
|
| 42826 |
+
"grad_norm": 0.196293443441391,
|
| 42827 |
+
"learning_rate": 3.832178862454303e-05,
|
| 42828 |
+
"loss": 0.7117,
|
| 42829 |
+
"step": 6117
|
| 42830 |
+
},
|
| 42831 |
+
{
|
| 42832 |
+
"epoch": 6.968660968660968,
|
| 42833 |
+
"grad_norm": 0.1941792070865631,
|
| 42834 |
+
"learning_rate": 3.831784581210002e-05,
|
| 42835 |
+
"loss": 0.6874,
|
| 42836 |
+
"step": 6118
|
| 42837 |
+
},
|
| 42838 |
+
{
|
| 42839 |
+
"epoch": 6.96980056980057,
|
| 42840 |
+
"grad_norm": 0.19943450391292572,
|
| 42841 |
+
"learning_rate": 3.831390253709159e-05,
|
| 42842 |
+
"loss": 0.6166,
|
| 42843 |
+
"step": 6119
|
| 42844 |
+
},
|
| 42845 |
+
{
|
| 42846 |
+
"epoch": 6.970940170940171,
|
| 42847 |
+
"grad_norm": 0.17430053651332855,
|
| 42848 |
+
"learning_rate": 3.830995879965471e-05,
|
| 42849 |
+
"loss": 0.885,
|
| 42850 |
+
"step": 6120
|
| 42851 |
+
},
|
| 42852 |
+
{
|
| 42853 |
+
"epoch": 6.972079772079772,
|
| 42854 |
+
"grad_norm": 0.19655632972717285,
|
| 42855 |
+
"learning_rate": 3.8306014599926366e-05,
|
| 42856 |
+
"loss": 0.7789,
|
| 42857 |
+
"step": 6121
|
| 42858 |
+
},
|
| 42859 |
+
{
|
| 42860 |
+
"epoch": 6.973219373219373,
|
| 42861 |
+
"grad_norm": 0.19573719799518585,
|
| 42862 |
+
"learning_rate": 3.830206993804354e-05,
|
| 42863 |
+
"loss": 0.8234,
|
| 42864 |
+
"step": 6122
|
| 42865 |
+
},
|
| 42866 |
+
{
|
| 42867 |
+
"epoch": 6.9743589743589745,
|
| 42868 |
+
"grad_norm": 0.1745665967464447,
|
| 42869 |
+
"learning_rate": 3.829812481414325e-05,
|
| 42870 |
+
"loss": 0.6927,
|
| 42871 |
+
"step": 6123
|
| 42872 |
+
},
|
| 42873 |
+
{
|
| 42874 |
+
"epoch": 6.975498575498576,
|
| 42875 |
+
"grad_norm": 0.18195831775665283,
|
| 42876 |
+
"learning_rate": 3.8294179228362515e-05,
|
| 42877 |
+
"loss": 0.7576,
|
| 42878 |
+
"step": 6124
|
| 42879 |
+
},
|
| 42880 |
+
{
|
| 42881 |
+
"epoch": 6.976638176638176,
|
| 42882 |
+
"grad_norm": 0.22098475694656372,
|
| 42883 |
+
"learning_rate": 3.829023318083837e-05,
|
| 42884 |
+
"loss": 0.7319,
|
| 42885 |
+
"step": 6125
|
| 42886 |
+
},
|
| 42887 |
+
{
|
| 42888 |
+
"epoch": 6.977777777777778,
|
| 42889 |
+
"grad_norm": 0.22530747950077057,
|
| 42890 |
+
"learning_rate": 3.828628667170788e-05,
|
| 42891 |
+
"loss": 0.7975,
|
| 42892 |
+
"step": 6126
|
| 42893 |
+
},
|
| 42894 |
+
{
|
| 42895 |
+
"epoch": 6.978917378917379,
|
| 42896 |
+
"grad_norm": 0.1645485907793045,
|
| 42897 |
+
"learning_rate": 3.8282339701108115e-05,
|
| 42898 |
+
"loss": 0.7984,
|
| 42899 |
+
"step": 6127
|
| 42900 |
+
},
|
| 42901 |
+
{
|
| 42902 |
+
"epoch": 6.98005698005698,
|
| 42903 |
+
"grad_norm": 0.16129399836063385,
|
| 42904 |
+
"learning_rate": 3.8278392269176175e-05,
|
| 42905 |
+
"loss": 0.8035,
|
| 42906 |
+
"step": 6128
|
| 42907 |
+
},
|
| 42908 |
+
{
|
| 42909 |
+
"epoch": 6.981196581196581,
|
| 42910 |
+
"grad_norm": 0.2013663351535797,
|
| 42911 |
+
"learning_rate": 3.827444437604915e-05,
|
| 42912 |
+
"loss": 0.6483,
|
| 42913 |
+
"step": 6129
|
| 42914 |
+
},
|
| 42915 |
+
{
|
| 42916 |
+
"epoch": 6.982336182336183,
|
| 42917 |
+
"grad_norm": 0.16806060075759888,
|
| 42918 |
+
"learning_rate": 3.827049602186416e-05,
|
| 42919 |
+
"loss": 0.6591,
|
| 42920 |
+
"step": 6130
|
| 42921 |
+
},
|
| 42922 |
+
{
|
| 42923 |
+
"epoch": 6.983475783475783,
|
| 42924 |
+
"grad_norm": 0.1734466850757599,
|
| 42925 |
+
"learning_rate": 3.826654720675835e-05,
|
| 42926 |
+
"loss": 0.8583,
|
| 42927 |
+
"step": 6131
|
| 42928 |
+
},
|
| 42929 |
+
{
|
| 42930 |
+
"epoch": 6.984615384615385,
|
| 42931 |
+
"grad_norm": 0.19261620938777924,
|
| 42932 |
+
"learning_rate": 3.826259793086888e-05,
|
| 42933 |
+
"loss": 0.6961,
|
| 42934 |
+
"step": 6132
|
| 42935 |
+
},
|
| 42936 |
+
{
|
| 42937 |
+
"epoch": 6.985754985754986,
|
| 42938 |
+
"grad_norm": 0.1568852961063385,
|
| 42939 |
+
"learning_rate": 3.825864819433291e-05,
|
| 42940 |
+
"loss": 0.8037,
|
| 42941 |
+
"step": 6133
|
| 42942 |
+
},
|
| 42943 |
+
{
|
| 42944 |
+
"epoch": 6.986894586894587,
|
| 42945 |
+
"grad_norm": 0.17459647357463837,
|
| 42946 |
+
"learning_rate": 3.8254697997287624e-05,
|
| 42947 |
+
"loss": 0.8462,
|
| 42948 |
+
"step": 6134
|
| 42949 |
+
},
|
| 42950 |
+
{
|
| 42951 |
+
"epoch": 6.988034188034188,
|
| 42952 |
+
"grad_norm": 0.16817878186702728,
|
| 42953 |
+
"learning_rate": 3.825074733987023e-05,
|
| 42954 |
+
"loss": 0.8529,
|
| 42955 |
+
"step": 6135
|
| 42956 |
+
},
|
| 42957 |
+
{
|
| 42958 |
+
"epoch": 6.9891737891737895,
|
| 42959 |
+
"grad_norm": 0.17553623020648956,
|
| 42960 |
+
"learning_rate": 3.824679622221794e-05,
|
| 42961 |
+
"loss": 0.8571,
|
| 42962 |
+
"step": 6136
|
| 42963 |
+
},
|
| 42964 |
+
{
|
| 42965 |
+
"epoch": 6.99031339031339,
|
| 42966 |
+
"grad_norm": 0.14740072190761566,
|
| 42967 |
+
"learning_rate": 3.824284464446799e-05,
|
| 42968 |
+
"loss": 0.9423,
|
| 42969 |
+
"step": 6137
|
| 42970 |
+
},
|
| 42971 |
+
{
|
| 42972 |
+
"epoch": 6.9914529914529915,
|
| 42973 |
+
"grad_norm": 0.17177456617355347,
|
| 42974 |
+
"learning_rate": 3.823889260675763e-05,
|
| 42975 |
+
"loss": 0.7721,
|
| 42976 |
+
"step": 6138
|
| 42977 |
+
},
|
| 42978 |
+
{
|
| 42979 |
+
"epoch": 6.992592592592593,
|
| 42980 |
+
"grad_norm": 0.17124785482883453,
|
| 42981 |
+
"learning_rate": 3.823494010922411e-05,
|
| 42982 |
+
"loss": 0.777,
|
| 42983 |
+
"step": 6139
|
| 42984 |
+
},
|
| 42985 |
+
{
|
| 42986 |
+
"epoch": 6.9937321937321935,
|
| 42987 |
+
"grad_norm": 0.19509488344192505,
|
| 42988 |
+
"learning_rate": 3.823098715200473e-05,
|
| 42989 |
+
"loss": 0.7244,
|
| 42990 |
+
"step": 6140
|
| 42991 |
+
},
|
| 42992 |
+
{
|
| 42993 |
+
"epoch": 6.994871794871795,
|
| 42994 |
+
"grad_norm": 0.17017509043216705,
|
| 42995 |
+
"learning_rate": 3.8227033735236784e-05,
|
| 42996 |
+
"loss": 0.9012,
|
| 42997 |
+
"step": 6141
|
| 42998 |
+
},
|
| 42999 |
+
{
|
| 43000 |
+
"epoch": 6.996011396011396,
|
| 43001 |
+
"grad_norm": 0.18812443315982819,
|
| 43002 |
+
"learning_rate": 3.8223079859057575e-05,
|
| 43003 |
+
"loss": 0.8421,
|
| 43004 |
+
"step": 6142
|
| 43005 |
+
},
|
| 43006 |
+
{
|
| 43007 |
+
"epoch": 6.997150997150997,
|
| 43008 |
+
"grad_norm": 0.1462877094745636,
|
| 43009 |
+
"learning_rate": 3.821912552360445e-05,
|
| 43010 |
+
"loss": 0.8403,
|
| 43011 |
+
"step": 6143
|
| 43012 |
+
},
|
| 43013 |
+
{
|
| 43014 |
+
"epoch": 6.998290598290598,
|
| 43015 |
+
"grad_norm": 0.17546626925468445,
|
| 43016 |
+
"learning_rate": 3.821517072901474e-05,
|
| 43017 |
+
"loss": 0.7151,
|
| 43018 |
+
"step": 6144
|
| 43019 |
+
},
|
| 43020 |
+
{
|
| 43021 |
+
"epoch": 6.9994301994302,
|
| 43022 |
+
"grad_norm": 0.2128238081932068,
|
| 43023 |
+
"learning_rate": 3.82112154754258e-05,
|
| 43024 |
+
"loss": 0.6944,
|
| 43025 |
+
"step": 6145
|
| 43026 |
+
},
|
| 43027 |
+
{
|
| 43028 |
+
"epoch": 7.0,
|
| 43029 |
+
"grad_norm": 0.5616998672485352,
|
| 43030 |
+
"learning_rate": 3.820725976297502e-05,
|
| 43031 |
+
"loss": 0.222,
|
| 43032 |
+
"step": 6146
|
| 43033 |
+
},
|
| 43034 |
+
{
|
| 43035 |
+
"epoch": 7.001139601139601,
|
| 43036 |
+
"grad_norm": 0.15877407789230347,
|
| 43037 |
+
"learning_rate": 3.820330359179979e-05,
|
| 43038 |
+
"loss": 0.7071,
|
| 43039 |
+
"step": 6147
|
| 43040 |
+
},
|
| 43041 |
+
{
|
| 43042 |
+
"epoch": 7.002279202279202,
|
| 43043 |
+
"grad_norm": 0.21806888282299042,
|
| 43044 |
+
"learning_rate": 3.819934696203752e-05,
|
| 43045 |
+
"loss": 0.782,
|
| 43046 |
+
"step": 6148
|
| 43047 |
+
},
|
| 43048 |
+
{
|
| 43049 |
+
"epoch": 7.003418803418803,
|
| 43050 |
+
"grad_norm": 0.20868085324764252,
|
| 43051 |
+
"learning_rate": 3.819538987382562e-05,
|
| 43052 |
+
"loss": 0.6292,
|
| 43053 |
+
"step": 6149
|
| 43054 |
+
},
|
| 43055 |
+
{
|
| 43056 |
+
"epoch": 7.004558404558405,
|
| 43057 |
+
"grad_norm": 0.22230400145053864,
|
| 43058 |
+
"learning_rate": 3.8191432327301556e-05,
|
| 43059 |
+
"loss": 0.7988,
|
| 43060 |
+
"step": 6150
|
| 43061 |
+
},
|
| 43062 |
+
{
|
| 43063 |
+
"epoch": 7.005698005698005,
|
| 43064 |
+
"grad_norm": 0.1857542246580124,
|
| 43065 |
+
"learning_rate": 3.818747432260276e-05,
|
| 43066 |
+
"loss": 0.7849,
|
| 43067 |
+
"step": 6151
|
| 43068 |
+
},
|
| 43069 |
+
{
|
| 43070 |
+
"epoch": 7.006837606837607,
|
| 43071 |
+
"grad_norm": 0.17437143623828888,
|
| 43072 |
+
"learning_rate": 3.818351585986673e-05,
|
| 43073 |
+
"loss": 0.819,
|
| 43074 |
+
"step": 6152
|
| 43075 |
+
},
|
| 43076 |
+
{
|
| 43077 |
+
"epoch": 7.007977207977208,
|
| 43078 |
+
"grad_norm": 0.19998261332511902,
|
| 43079 |
+
"learning_rate": 3.817955693923092e-05,
|
| 43080 |
+
"loss": 0.773,
|
| 43081 |
+
"step": 6153
|
| 43082 |
+
},
|
| 43083 |
+
{
|
| 43084 |
+
"epoch": 7.009116809116809,
|
| 43085 |
+
"grad_norm": 0.18506497144699097,
|
| 43086 |
+
"learning_rate": 3.817559756083287e-05,
|
| 43087 |
+
"loss": 0.7527,
|
| 43088 |
+
"step": 6154
|
| 43089 |
+
},
|
| 43090 |
+
{
|
| 43091 |
+
"epoch": 7.01025641025641,
|
| 43092 |
+
"grad_norm": 0.17287065088748932,
|
| 43093 |
+
"learning_rate": 3.817163772481007e-05,
|
| 43094 |
+
"loss": 0.8289,
|
| 43095 |
+
"step": 6155
|
| 43096 |
+
},
|
| 43097 |
+
{
|
| 43098 |
+
"epoch": 7.011396011396012,
|
| 43099 |
+
"grad_norm": 0.20515497028827667,
|
| 43100 |
+
"learning_rate": 3.816767743130008e-05,
|
| 43101 |
+
"loss": 0.6524,
|
| 43102 |
+
"step": 6156
|
| 43103 |
+
},
|
| 43104 |
+
{
|
| 43105 |
+
"epoch": 7.012535612535612,
|
| 43106 |
+
"grad_norm": 0.22639547288417816,
|
| 43107 |
+
"learning_rate": 3.8163716680440444e-05,
|
| 43108 |
+
"loss": 0.5337,
|
| 43109 |
+
"step": 6157
|
| 43110 |
+
},
|
| 43111 |
+
{
|
| 43112 |
+
"epoch": 7.013675213675214,
|
| 43113 |
+
"grad_norm": 0.23270073533058167,
|
| 43114 |
+
"learning_rate": 3.8159755472368716e-05,
|
| 43115 |
+
"loss": 0.6143,
|
| 43116 |
+
"step": 6158
|
| 43117 |
+
},
|
| 43118 |
+
{
|
| 43119 |
+
"epoch": 7.014814814814815,
|
| 43120 |
+
"grad_norm": 0.19774219393730164,
|
| 43121 |
+
"learning_rate": 3.815579380722249e-05,
|
| 43122 |
+
"loss": 0.7952,
|
| 43123 |
+
"step": 6159
|
| 43124 |
+
},
|
| 43125 |
+
{
|
| 43126 |
+
"epoch": 7.015954415954416,
|
| 43127 |
+
"grad_norm": 0.21318969130516052,
|
| 43128 |
+
"learning_rate": 3.815183168513937e-05,
|
| 43129 |
+
"loss": 0.7876,
|
| 43130 |
+
"step": 6160
|
| 43131 |
+
},
|
| 43132 |
+
{
|
| 43133 |
+
"epoch": 7.017094017094017,
|
| 43134 |
+
"grad_norm": 0.1774902492761612,
|
| 43135 |
+
"learning_rate": 3.814786910625698e-05,
|
| 43136 |
+
"loss": 0.7481,
|
| 43137 |
+
"step": 6161
|
| 43138 |
+
},
|
| 43139 |
+
{
|
| 43140 |
+
"epoch": 7.0182336182336185,
|
| 43141 |
+
"grad_norm": 0.19848689436912537,
|
| 43142 |
+
"learning_rate": 3.814390607071293e-05,
|
| 43143 |
+
"loss": 0.7195,
|
| 43144 |
+
"step": 6162
|
| 43145 |
+
},
|
| 43146 |
+
{
|
| 43147 |
+
"epoch": 7.019373219373219,
|
| 43148 |
+
"grad_norm": 0.19199149310588837,
|
| 43149 |
+
"learning_rate": 3.813994257864487e-05,
|
| 43150 |
+
"loss": 0.6329,
|
| 43151 |
+
"step": 6163
|
| 43152 |
+
},
|
| 43153 |
+
{
|
| 43154 |
+
"epoch": 7.02051282051282,
|
| 43155 |
+
"grad_norm": 0.15332777798175812,
|
| 43156 |
+
"learning_rate": 3.8135978630190475e-05,
|
| 43157 |
+
"loss": 0.8689,
|
| 43158 |
+
"step": 6164
|
| 43159 |
+
},
|
| 43160 |
+
{
|
| 43161 |
+
"epoch": 7.021652421652422,
|
| 43162 |
+
"grad_norm": 0.21588227152824402,
|
| 43163 |
+
"learning_rate": 3.813201422548742e-05,
|
| 43164 |
+
"loss": 0.7189,
|
| 43165 |
+
"step": 6165
|
| 43166 |
+
},
|
| 43167 |
+
{
|
| 43168 |
+
"epoch": 7.022792022792022,
|
| 43169 |
+
"grad_norm": 0.16512146592140198,
|
| 43170 |
+
"learning_rate": 3.812804936467339e-05,
|
| 43171 |
+
"loss": 0.7091,
|
| 43172 |
+
"step": 6166
|
| 43173 |
+
},
|
| 43174 |
+
{
|
| 43175 |
+
"epoch": 7.023931623931624,
|
| 43176 |
+
"grad_norm": 0.17718267440795898,
|
| 43177 |
+
"learning_rate": 3.812408404788612e-05,
|
| 43178 |
+
"loss": 0.8396,
|
| 43179 |
+
"step": 6167
|
| 43180 |
+
},
|
| 43181 |
+
{
|
| 43182 |
+
"epoch": 7.025071225071225,
|
| 43183 |
+
"grad_norm": 0.1793379932641983,
|
| 43184 |
+
"learning_rate": 3.81201182752633e-05,
|
| 43185 |
+
"loss": 0.7302,
|
| 43186 |
+
"step": 6168
|
| 43187 |
+
},
|
| 43188 |
+
{
|
| 43189 |
+
"epoch": 7.026210826210826,
|
| 43190 |
+
"grad_norm": 0.2009889781475067,
|
| 43191 |
+
"learning_rate": 3.811615204694271e-05,
|
| 43192 |
+
"loss": 0.6743,
|
| 43193 |
+
"step": 6169
|
| 43194 |
+
},
|
| 43195 |
+
{
|
| 43196 |
+
"epoch": 7.027350427350427,
|
| 43197 |
+
"grad_norm": 0.19245830178260803,
|
| 43198 |
+
"learning_rate": 3.811218536306208e-05,
|
| 43199 |
+
"loss": 0.7848,
|
| 43200 |
+
"step": 6170
|
| 43201 |
+
},
|
| 43202 |
+
{
|
| 43203 |
+
"epoch": 7.028490028490029,
|
| 43204 |
+
"grad_norm": 0.1399477869272232,
|
| 43205 |
+
"learning_rate": 3.810821822375919e-05,
|
| 43206 |
+
"loss": 0.8796,
|
| 43207 |
+
"step": 6171
|
| 43208 |
+
},
|
| 43209 |
+
{
|
| 43210 |
+
"epoch": 7.029629629629629,
|
| 43211 |
+
"grad_norm": 0.15103209018707275,
|
| 43212 |
+
"learning_rate": 3.810425062917184e-05,
|
| 43213 |
+
"loss": 0.8595,
|
| 43214 |
+
"step": 6172
|
| 43215 |
+
},
|
| 43216 |
+
{
|
| 43217 |
+
"epoch": 7.030769230769231,
|
| 43218 |
+
"grad_norm": 0.16661714017391205,
|
| 43219 |
+
"learning_rate": 3.810028257943783e-05,
|
| 43220 |
+
"loss": 0.7775,
|
| 43221 |
+
"step": 6173
|
| 43222 |
+
},
|
| 43223 |
+
{
|
| 43224 |
+
"epoch": 7.031908831908832,
|
| 43225 |
+
"grad_norm": 0.3529140055179596,
|
| 43226 |
+
"learning_rate": 3.809631407469497e-05,
|
| 43227 |
+
"loss": 0.8598,
|
| 43228 |
+
"step": 6174
|
| 43229 |
+
},
|
| 43230 |
+
{
|
| 43231 |
+
"epoch": 7.033048433048433,
|
| 43232 |
+
"grad_norm": 0.1784033477306366,
|
| 43233 |
+
"learning_rate": 3.809234511508111e-05,
|
| 43234 |
+
"loss": 0.6518,
|
| 43235 |
+
"step": 6175
|
| 43236 |
+
},
|
| 43237 |
+
{
|
| 43238 |
+
"epoch": 7.034188034188034,
|
| 43239 |
+
"grad_norm": 0.15606975555419922,
|
| 43240 |
+
"learning_rate": 3.808837570073411e-05,
|
| 43241 |
+
"loss": 0.9845,
|
| 43242 |
+
"step": 6176
|
| 43243 |
+
},
|
| 43244 |
+
{
|
| 43245 |
+
"epoch": 7.0353276353276355,
|
| 43246 |
+
"grad_norm": 0.19400037825107574,
|
| 43247 |
+
"learning_rate": 3.808440583179182e-05,
|
| 43248 |
+
"loss": 0.7577,
|
| 43249 |
+
"step": 6177
|
| 43250 |
+
},
|
| 43251 |
+
{
|
| 43252 |
+
"epoch": 7.036467236467236,
|
| 43253 |
+
"grad_norm": 0.16465899348258972,
|
| 43254 |
+
"learning_rate": 3.808043550839214e-05,
|
| 43255 |
+
"loss": 0.9296,
|
| 43256 |
+
"step": 6178
|
| 43257 |
+
},
|
| 43258 |
+
{
|
| 43259 |
+
"epoch": 7.0376068376068375,
|
| 43260 |
+
"grad_norm": 0.20099498331546783,
|
| 43261 |
+
"learning_rate": 3.807646473067296e-05,
|
| 43262 |
+
"loss": 0.7348,
|
| 43263 |
+
"step": 6179
|
| 43264 |
+
},
|
| 43265 |
+
{
|
| 43266 |
+
"epoch": 7.038746438746439,
|
| 43267 |
+
"grad_norm": 0.21224263310432434,
|
| 43268 |
+
"learning_rate": 3.80724934987722e-05,
|
| 43269 |
+
"loss": 0.6274,
|
| 43270 |
+
"step": 6180
|
| 43271 |
+
},
|
| 43272 |
+
{
|
| 43273 |
+
"epoch": 7.0398860398860394,
|
| 43274 |
+
"grad_norm": 0.18550077080726624,
|
| 43275 |
+
"learning_rate": 3.8068521812827786e-05,
|
| 43276 |
+
"loss": 0.7556,
|
| 43277 |
+
"step": 6181
|
| 43278 |
+
},
|
| 43279 |
+
{
|
| 43280 |
+
"epoch": 7.041025641025641,
|
| 43281 |
+
"grad_norm": 0.17198899388313293,
|
| 43282 |
+
"learning_rate": 3.806454967297768e-05,
|
| 43283 |
+
"loss": 0.8068,
|
| 43284 |
+
"step": 6182
|
| 43285 |
+
},
|
| 43286 |
+
{
|
| 43287 |
+
"epoch": 7.042165242165242,
|
| 43288 |
+
"grad_norm": 0.19705481827259064,
|
| 43289 |
+
"learning_rate": 3.806057707935983e-05,
|
| 43290 |
+
"loss": 0.658,
|
| 43291 |
+
"step": 6183
|
| 43292 |
+
},
|
| 43293 |
+
{
|
| 43294 |
+
"epoch": 7.043304843304844,
|
| 43295 |
+
"grad_norm": 0.16149069368839264,
|
| 43296 |
+
"learning_rate": 3.805660403211222e-05,
|
| 43297 |
+
"loss": 0.8061,
|
| 43298 |
+
"step": 6184
|
| 43299 |
+
},
|
| 43300 |
+
{
|
| 43301 |
+
"epoch": 7.044444444444444,
|
| 43302 |
+
"grad_norm": 0.22355586290359497,
|
| 43303 |
+
"learning_rate": 3.805263053137285e-05,
|
| 43304 |
+
"loss": 0.6092,
|
| 43305 |
+
"step": 6185
|
| 43306 |
+
},
|
| 43307 |
+
{
|
| 43308 |
+
"epoch": 7.045584045584046,
|
| 43309 |
+
"grad_norm": 0.19000141322612762,
|
| 43310 |
+
"learning_rate": 3.804865657727972e-05,
|
| 43311 |
+
"loss": 0.7292,
|
| 43312 |
+
"step": 6186
|
| 43313 |
+
},
|
| 43314 |
+
{
|
| 43315 |
+
"epoch": 7.046723646723647,
|
| 43316 |
+
"grad_norm": 0.1919831931591034,
|
| 43317 |
+
"learning_rate": 3.804468216997087e-05,
|
| 43318 |
+
"loss": 0.7595,
|
| 43319 |
+
"step": 6187
|
| 43320 |
+
},
|
| 43321 |
+
{
|
| 43322 |
+
"epoch": 7.047863247863248,
|
| 43323 |
+
"grad_norm": 0.19090311229228973,
|
| 43324 |
+
"learning_rate": 3.804070730958433e-05,
|
| 43325 |
+
"loss": 0.8146,
|
| 43326 |
+
"step": 6188
|
| 43327 |
+
},
|
| 43328 |
+
{
|
| 43329 |
+
"epoch": 7.049002849002849,
|
| 43330 |
+
"grad_norm": 0.15896199643611908,
|
| 43331 |
+
"learning_rate": 3.8036731996258176e-05,
|
| 43332 |
+
"loss": 0.7582,
|
| 43333 |
+
"step": 6189
|
| 43334 |
+
},
|
| 43335 |
+
{
|
| 43336 |
+
"epoch": 7.050142450142451,
|
| 43337 |
+
"grad_norm": 0.16467316448688507,
|
| 43338 |
+
"learning_rate": 3.8032756230130455e-05,
|
| 43339 |
+
"loss": 0.9001,
|
| 43340 |
+
"step": 6190
|
| 43341 |
+
},
|
| 43342 |
+
{
|
| 43343 |
+
"epoch": 7.051282051282051,
|
| 43344 |
+
"grad_norm": 0.23392154276371002,
|
| 43345 |
+
"learning_rate": 3.802878001133928e-05,
|
| 43346 |
+
"loss": 0.8469,
|
| 43347 |
+
"step": 6191
|
| 43348 |
+
},
|
| 43349 |
+
{
|
| 43350 |
+
"epoch": 7.0524216524216525,
|
| 43351 |
+
"grad_norm": 0.20221088826656342,
|
| 43352 |
+
"learning_rate": 3.802480334002273e-05,
|
| 43353 |
+
"loss": 0.7333,
|
| 43354 |
+
"step": 6192
|
| 43355 |
+
},
|
| 43356 |
+
{
|
| 43357 |
+
"epoch": 7.053561253561254,
|
| 43358 |
+
"grad_norm": 0.1554950475692749,
|
| 43359 |
+
"learning_rate": 3.802082621631896e-05,
|
| 43360 |
+
"loss": 0.8843,
|
| 43361 |
+
"step": 6193
|
| 43362 |
+
},
|
| 43363 |
+
{
|
| 43364 |
+
"epoch": 7.0547008547008545,
|
| 43365 |
+
"grad_norm": 0.16900935769081116,
|
| 43366 |
+
"learning_rate": 3.801684864036608e-05,
|
| 43367 |
+
"loss": 0.9239,
|
| 43368 |
+
"step": 6194
|
| 43369 |
+
},
|
| 43370 |
+
{
|
| 43371 |
+
"epoch": 7.055840455840456,
|
| 43372 |
+
"grad_norm": 0.1725151687860489,
|
| 43373 |
+
"learning_rate": 3.801287061230225e-05,
|
| 43374 |
+
"loss": 0.8127,
|
| 43375 |
+
"step": 6195
|
| 43376 |
+
},
|
| 43377 |
+
{
|
| 43378 |
+
"epoch": 7.056980056980057,
|
| 43379 |
+
"grad_norm": 0.19210198521614075,
|
| 43380 |
+
"learning_rate": 3.800889213226564e-05,
|
| 43381 |
+
"loss": 0.7209,
|
| 43382 |
+
"step": 6196
|
| 43383 |
+
},
|
| 43384 |
+
{
|
| 43385 |
+
"epoch": 7.058119658119658,
|
| 43386 |
+
"grad_norm": 0.1677943915128708,
|
| 43387 |
+
"learning_rate": 3.8004913200394424e-05,
|
| 43388 |
+
"loss": 0.8652,
|
| 43389 |
+
"step": 6197
|
| 43390 |
+
},
|
| 43391 |
+
{
|
| 43392 |
+
"epoch": 7.059259259259259,
|
| 43393 |
+
"grad_norm": 0.14735138416290283,
|
| 43394 |
+
"learning_rate": 3.800093381682682e-05,
|
| 43395 |
+
"loss": 1.0122,
|
| 43396 |
+
"step": 6198
|
| 43397 |
+
},
|
| 43398 |
+
{
|
| 43399 |
+
"epoch": 7.060398860398861,
|
| 43400 |
+
"grad_norm": 0.18274037539958954,
|
| 43401 |
+
"learning_rate": 3.799695398170102e-05,
|
| 43402 |
+
"loss": 0.8897,
|
| 43403 |
+
"step": 6199
|
| 43404 |
+
},
|
| 43405 |
+
{
|
| 43406 |
+
"epoch": 7.061538461538461,
|
| 43407 |
+
"grad_norm": 0.1837732344865799,
|
| 43408 |
+
"learning_rate": 3.799297369515528e-05,
|
| 43409 |
+
"loss": 0.8731,
|
| 43410 |
+
"step": 6200
|
| 43411 |
+
},
|
| 43412 |
+
{
|
| 43413 |
+
"epoch": 7.062678062678063,
|
| 43414 |
+
"grad_norm": 0.21213854849338531,
|
| 43415 |
+
"learning_rate": 3.798899295732782e-05,
|
| 43416 |
+
"loss": 0.6061,
|
| 43417 |
+
"step": 6201
|
| 43418 |
+
},
|
| 43419 |
+
{
|
| 43420 |
+
"epoch": 7.063817663817664,
|
| 43421 |
+
"grad_norm": 0.20559147000312805,
|
| 43422 |
+
"learning_rate": 3.798501176835693e-05,
|
| 43423 |
+
"loss": 0.7465,
|
| 43424 |
+
"step": 6202
|
| 43425 |
+
},
|
| 43426 |
+
{
|
| 43427 |
+
"epoch": 7.064957264957265,
|
| 43428 |
+
"grad_norm": 0.20526240766048431,
|
| 43429 |
+
"learning_rate": 3.798103012838086e-05,
|
| 43430 |
+
"loss": 0.7046,
|
| 43431 |
+
"step": 6203
|
| 43432 |
+
},
|
| 43433 |
+
{
|
| 43434 |
+
"epoch": 7.066096866096866,
|
| 43435 |
+
"grad_norm": 0.18055404722690582,
|
| 43436 |
+
"learning_rate": 3.7977048037537915e-05,
|
| 43437 |
+
"loss": 0.9445,
|
| 43438 |
+
"step": 6204
|
| 43439 |
+
},
|
| 43440 |
+
{
|
| 43441 |
+
"epoch": 7.067236467236468,
|
| 43442 |
+
"grad_norm": 0.19590269029140472,
|
| 43443 |
+
"learning_rate": 3.797306549596641e-05,
|
| 43444 |
+
"loss": 0.6855,
|
| 43445 |
+
"step": 6205
|
| 43446 |
+
},
|
| 43447 |
+
{
|
| 43448 |
+
"epoch": 7.068376068376068,
|
| 43449 |
+
"grad_norm": 0.18099546432495117,
|
| 43450 |
+
"learning_rate": 3.7969082503804666e-05,
|
| 43451 |
+
"loss": 0.833,
|
| 43452 |
+
"step": 6206
|
| 43453 |
+
},
|
| 43454 |
+
{
|
| 43455 |
+
"epoch": 7.06951566951567,
|
| 43456 |
+
"grad_norm": 0.17715154588222504,
|
| 43457 |
+
"learning_rate": 3.796509906119101e-05,
|
| 43458 |
+
"loss": 0.6798,
|
| 43459 |
+
"step": 6207
|
| 43460 |
+
},
|
| 43461 |
+
{
|
| 43462 |
+
"epoch": 7.070655270655271,
|
| 43463 |
+
"grad_norm": 0.1813538521528244,
|
| 43464 |
+
"learning_rate": 3.796111516826382e-05,
|
| 43465 |
+
"loss": 0.7816,
|
| 43466 |
+
"step": 6208
|
| 43467 |
+
},
|
| 43468 |
+
{
|
| 43469 |
+
"epoch": 7.0717948717948715,
|
| 43470 |
+
"grad_norm": 0.1964096575975418,
|
| 43471 |
+
"learning_rate": 3.795713082516145e-05,
|
| 43472 |
+
"loss": 0.7283,
|
| 43473 |
+
"step": 6209
|
| 43474 |
+
},
|
| 43475 |
+
{
|
| 43476 |
+
"epoch": 7.072934472934473,
|
| 43477 |
+
"grad_norm": 0.15161927044391632,
|
| 43478 |
+
"learning_rate": 3.7953146032022304e-05,
|
| 43479 |
+
"loss": 0.8643,
|
| 43480 |
+
"step": 6210
|
| 43481 |
+
},
|
| 43482 |
+
{
|
| 43483 |
+
"epoch": 7.074074074074074,
|
| 43484 |
+
"grad_norm": 0.17454886436462402,
|
| 43485 |
+
"learning_rate": 3.794916078898477e-05,
|
| 43486 |
+
"loss": 0.6843,
|
| 43487 |
+
"step": 6211
|
| 43488 |
+
},
|
| 43489 |
+
{
|
| 43490 |
+
"epoch": 7.075213675213675,
|
| 43491 |
+
"grad_norm": 0.19816745817661285,
|
| 43492 |
+
"learning_rate": 3.7945175096187275e-05,
|
| 43493 |
+
"loss": 0.7673,
|
| 43494 |
+
"step": 6212
|
| 43495 |
+
},
|
| 43496 |
+
{
|
| 43497 |
+
"epoch": 7.076353276353276,
|
| 43498 |
+
"grad_norm": 0.1860775649547577,
|
| 43499 |
+
"learning_rate": 3.794118895376824e-05,
|
| 43500 |
+
"loss": 0.6416,
|
| 43501 |
+
"step": 6213
|
| 43502 |
+
},
|
| 43503 |
+
{
|
| 43504 |
+
"epoch": 7.077492877492878,
|
| 43505 |
+
"grad_norm": 0.17332245409488678,
|
| 43506 |
+
"learning_rate": 3.793720236186613e-05,
|
| 43507 |
+
"loss": 0.7829,
|
| 43508 |
+
"step": 6214
|
| 43509 |
+
},
|
| 43510 |
+
{
|
| 43511 |
+
"epoch": 7.078632478632478,
|
| 43512 |
+
"grad_norm": 0.16401895880699158,
|
| 43513 |
+
"learning_rate": 3.793321532061941e-05,
|
| 43514 |
+
"loss": 0.7432,
|
| 43515 |
+
"step": 6215
|
| 43516 |
+
},
|
| 43517 |
+
{
|
| 43518 |
+
"epoch": 7.07977207977208,
|
| 43519 |
+
"grad_norm": 0.2050887644290924,
|
| 43520 |
+
"learning_rate": 3.7929227830166546e-05,
|
| 43521 |
+
"loss": 0.6448,
|
| 43522 |
+
"step": 6216
|
| 43523 |
+
},
|
| 43524 |
+
{
|
| 43525 |
+
"epoch": 7.080911680911681,
|
| 43526 |
+
"grad_norm": 0.1812848299741745,
|
| 43527 |
+
"learning_rate": 3.792523989064605e-05,
|
| 43528 |
+
"loss": 0.6495,
|
| 43529 |
+
"step": 6217
|
| 43530 |
+
},
|
| 43531 |
+
{
|
| 43532 |
+
"epoch": 7.082051282051282,
|
| 43533 |
+
"grad_norm": 0.17025980353355408,
|
| 43534 |
+
"learning_rate": 3.792125150219643e-05,
|
| 43535 |
+
"loss": 0.7915,
|
| 43536 |
+
"step": 6218
|
| 43537 |
+
},
|
| 43538 |
+
{
|
| 43539 |
+
"epoch": 7.083190883190883,
|
| 43540 |
+
"grad_norm": 0.19045335054397583,
|
| 43541 |
+
"learning_rate": 3.79172626649562e-05,
|
| 43542 |
+
"loss": 0.6843,
|
| 43543 |
+
"step": 6219
|
| 43544 |
+
},
|
| 43545 |
+
{
|
| 43546 |
+
"epoch": 7.084330484330485,
|
| 43547 |
+
"grad_norm": 0.21706286072731018,
|
| 43548 |
+
"learning_rate": 3.791327337906392e-05,
|
| 43549 |
+
"loss": 0.7377,
|
| 43550 |
+
"step": 6220
|
| 43551 |
+
},
|
| 43552 |
+
{
|
| 43553 |
+
"epoch": 7.085470085470085,
|
| 43554 |
+
"grad_norm": 0.206889346241951,
|
| 43555 |
+
"learning_rate": 3.7909283644658155e-05,
|
| 43556 |
+
"loss": 0.7257,
|
| 43557 |
+
"step": 6221
|
| 43558 |
+
},
|
| 43559 |
+
{
|
| 43560 |
+
"epoch": 7.086609686609687,
|
| 43561 |
+
"grad_norm": 0.15829861164093018,
|
| 43562 |
+
"learning_rate": 3.7905293461877456e-05,
|
| 43563 |
+
"loss": 0.7652,
|
| 43564 |
+
"step": 6222
|
| 43565 |
+
},
|
| 43566 |
+
{
|
| 43567 |
+
"epoch": 7.087749287749288,
|
| 43568 |
+
"grad_norm": 0.15279674530029297,
|
| 43569 |
+
"learning_rate": 3.790130283086043e-05,
|
| 43570 |
+
"loss": 0.9954,
|
| 43571 |
+
"step": 6223
|
| 43572 |
+
},
|
| 43573 |
+
{
|
| 43574 |
+
"epoch": 7.088888888888889,
|
| 43575 |
+
"grad_norm": 0.1945253312587738,
|
| 43576 |
+
"learning_rate": 3.789731175174568e-05,
|
| 43577 |
+
"loss": 0.7273,
|
| 43578 |
+
"step": 6224
|
| 43579 |
+
},
|
| 43580 |
+
{
|
| 43581 |
+
"epoch": 7.09002849002849,
|
| 43582 |
+
"grad_norm": 0.17092925310134888,
|
| 43583 |
+
"learning_rate": 3.7893320224671816e-05,
|
| 43584 |
+
"loss": 0.9352,
|
| 43585 |
+
"step": 6225
|
| 43586 |
+
},
|
| 43587 |
+
{
|
| 43588 |
+
"epoch": 7.091168091168091,
|
| 43589 |
+
"grad_norm": 0.17508654296398163,
|
| 43590 |
+
"learning_rate": 3.788932824977749e-05,
|
| 43591 |
+
"loss": 0.9059,
|
| 43592 |
+
"step": 6226
|
| 43593 |
+
},
|
| 43594 |
+
{
|
| 43595 |
+
"epoch": 7.092307692307692,
|
| 43596 |
+
"grad_norm": 0.17352032661437988,
|
| 43597 |
+
"learning_rate": 3.788533582720135e-05,
|
| 43598 |
+
"loss": 0.5925,
|
| 43599 |
+
"step": 6227
|
| 43600 |
+
},
|
| 43601 |
+
{
|
| 43602 |
+
"epoch": 7.093447293447293,
|
| 43603 |
+
"grad_norm": 0.16202287375926971,
|
| 43604 |
+
"learning_rate": 3.7881342957082064e-05,
|
| 43605 |
+
"loss": 0.8216,
|
| 43606 |
+
"step": 6228
|
| 43607 |
+
},
|
| 43608 |
+
{
|
| 43609 |
+
"epoch": 7.094586894586895,
|
| 43610 |
+
"grad_norm": 0.2091526836156845,
|
| 43611 |
+
"learning_rate": 3.787734963955831e-05,
|
| 43612 |
+
"loss": 0.7463,
|
| 43613 |
+
"step": 6229
|
| 43614 |
+
},
|
| 43615 |
+
{
|
| 43616 |
+
"epoch": 7.095726495726495,
|
| 43617 |
+
"grad_norm": 0.18009252846240997,
|
| 43618 |
+
"learning_rate": 3.787335587476879e-05,
|
| 43619 |
+
"loss": 0.8346,
|
| 43620 |
+
"step": 6230
|
| 43621 |
+
},
|
| 43622 |
+
{
|
| 43623 |
+
"epoch": 7.096866096866097,
|
| 43624 |
+
"grad_norm": 0.2047872245311737,
|
| 43625 |
+
"learning_rate": 3.786936166285221e-05,
|
| 43626 |
+
"loss": 0.6973,
|
| 43627 |
+
"step": 6231
|
| 43628 |
+
},
|
| 43629 |
+
{
|
| 43630 |
+
"epoch": 7.098005698005698,
|
| 43631 |
+
"grad_norm": 0.23231853544712067,
|
| 43632 |
+
"learning_rate": 3.7865367003947324e-05,
|
| 43633 |
+
"loss": 0.6047,
|
| 43634 |
+
"step": 6232
|
| 43635 |
+
},
|
| 43636 |
+
{
|
| 43637 |
+
"epoch": 7.099145299145299,
|
| 43638 |
+
"grad_norm": 0.19942378997802734,
|
| 43639 |
+
"learning_rate": 3.786137189819285e-05,
|
| 43640 |
+
"loss": 0.6073,
|
| 43641 |
+
"step": 6233
|
| 43642 |
+
},
|
| 43643 |
+
{
|
| 43644 |
+
"epoch": 7.1002849002849,
|
| 43645 |
+
"grad_norm": 0.18221347033977509,
|
| 43646 |
+
"learning_rate": 3.785737634572757e-05,
|
| 43647 |
+
"loss": 0.7227,
|
| 43648 |
+
"step": 6234
|
| 43649 |
+
},
|
| 43650 |
+
{
|
| 43651 |
+
"epoch": 7.101424501424502,
|
| 43652 |
+
"grad_norm": 0.15715356171131134,
|
| 43653 |
+
"learning_rate": 3.785338034669025e-05,
|
| 43654 |
+
"loss": 0.7622,
|
| 43655 |
+
"step": 6235
|
| 43656 |
+
},
|
| 43657 |
+
{
|
| 43658 |
+
"epoch": 7.102564102564102,
|
| 43659 |
+
"grad_norm": 0.16267679631710052,
|
| 43660 |
+
"learning_rate": 3.784938390121968e-05,
|
| 43661 |
+
"loss": 0.8677,
|
| 43662 |
+
"step": 6236
|
| 43663 |
+
},
|
| 43664 |
+
{
|
| 43665 |
+
"epoch": 7.103703703703704,
|
| 43666 |
+
"grad_norm": 0.193213552236557,
|
| 43667 |
+
"learning_rate": 3.784538700945467e-05,
|
| 43668 |
+
"loss": 0.7614,
|
| 43669 |
+
"step": 6237
|
| 43670 |
+
},
|
| 43671 |
+
{
|
| 43672 |
+
"epoch": 7.104843304843305,
|
| 43673 |
+
"grad_norm": 0.15954096615314484,
|
| 43674 |
+
"learning_rate": 3.784138967153405e-05,
|
| 43675 |
+
"loss": 0.8272,
|
| 43676 |
+
"step": 6238
|
| 43677 |
+
},
|
| 43678 |
+
{
|
| 43679 |
+
"epoch": 7.105982905982906,
|
| 43680 |
+
"grad_norm": 0.2050113081932068,
|
| 43681 |
+
"learning_rate": 3.783739188759665e-05,
|
| 43682 |
+
"loss": 0.7251,
|
| 43683 |
+
"step": 6239
|
| 43684 |
+
},
|
| 43685 |
+
{
|
| 43686 |
+
"epoch": 7.107122507122507,
|
| 43687 |
+
"grad_norm": 0.16363175213336945,
|
| 43688 |
+
"learning_rate": 3.783339365778132e-05,
|
| 43689 |
+
"loss": 0.914,
|
| 43690 |
+
"step": 6240
|
| 43691 |
+
},
|
| 43692 |
+
{
|
| 43693 |
+
"epoch": 7.1082621082621085,
|
| 43694 |
+
"grad_norm": 0.1950601041316986,
|
| 43695 |
+
"learning_rate": 3.782939498222695e-05,
|
| 43696 |
+
"loss": 0.7822,
|
| 43697 |
+
"step": 6241
|
| 43698 |
+
},
|
| 43699 |
+
{
|
| 43700 |
+
"epoch": 7.109401709401709,
|
| 43701 |
+
"grad_norm": 0.1943473368883133,
|
| 43702 |
+
"learning_rate": 3.78253958610724e-05,
|
| 43703 |
+
"loss": 0.7886,
|
| 43704 |
+
"step": 6242
|
| 43705 |
+
},
|
| 43706 |
+
{
|
| 43707 |
+
"epoch": 7.1105413105413104,
|
| 43708 |
+
"grad_norm": 0.15735872089862823,
|
| 43709 |
+
"learning_rate": 3.782139629445658e-05,
|
| 43710 |
+
"loss": 0.7819,
|
| 43711 |
+
"step": 6243
|
| 43712 |
+
},
|
| 43713 |
+
{
|
| 43714 |
+
"epoch": 7.111680911680912,
|
| 43715 |
+
"grad_norm": 0.18267220258712769,
|
| 43716 |
+
"learning_rate": 3.7817396282518424e-05,
|
| 43717 |
+
"loss": 0.7661,
|
| 43718 |
+
"step": 6244
|
| 43719 |
+
},
|
| 43720 |
+
{
|
| 43721 |
+
"epoch": 7.112820512820512,
|
| 43722 |
+
"grad_norm": 0.2050890028476715,
|
| 43723 |
+
"learning_rate": 3.781339582539684e-05,
|
| 43724 |
+
"loss": 0.6171,
|
| 43725 |
+
"step": 6245
|
| 43726 |
+
},
|
| 43727 |
+
{
|
| 43728 |
+
"epoch": 7.113960113960114,
|
| 43729 |
+
"grad_norm": 0.17580078542232513,
|
| 43730 |
+
"learning_rate": 3.780939492323077e-05,
|
| 43731 |
+
"loss": 1.0137,
|
| 43732 |
+
"step": 6246
|
| 43733 |
+
},
|
| 43734 |
+
{
|
| 43735 |
+
"epoch": 7.115099715099715,
|
| 43736 |
+
"grad_norm": 0.208582803606987,
|
| 43737 |
+
"learning_rate": 3.78053935761592e-05,
|
| 43738 |
+
"loss": 0.6083,
|
| 43739 |
+
"step": 6247
|
| 43740 |
+
},
|
| 43741 |
+
{
|
| 43742 |
+
"epoch": 7.116239316239316,
|
| 43743 |
+
"grad_norm": 0.16118314862251282,
|
| 43744 |
+
"learning_rate": 3.780139178432109e-05,
|
| 43745 |
+
"loss": 0.8084,
|
| 43746 |
+
"step": 6248
|
| 43747 |
+
},
|
| 43748 |
+
{
|
| 43749 |
+
"epoch": 7.117378917378917,
|
| 43750 |
+
"grad_norm": 0.16538970172405243,
|
| 43751 |
+
"learning_rate": 3.7797389547855443e-05,
|
| 43752 |
+
"loss": 0.8528,
|
| 43753 |
+
"step": 6249
|
| 43754 |
+
},
|
| 43755 |
+
{
|
| 43756 |
+
"epoch": 7.118518518518519,
|
| 43757 |
+
"grad_norm": 0.16062673926353455,
|
| 43758 |
+
"learning_rate": 3.779338686690126e-05,
|
| 43759 |
+
"loss": 0.7595,
|
| 43760 |
+
"step": 6250
|
| 43761 |
+
},
|
| 43762 |
+
{
|
| 43763 |
+
"epoch": 7.119658119658119,
|
| 43764 |
+
"grad_norm": 0.2156619429588318,
|
| 43765 |
+
"learning_rate": 3.778938374159758e-05,
|
| 43766 |
+
"loss": 0.6719,
|
| 43767 |
+
"step": 6251
|
| 43768 |
+
},
|
| 43769 |
+
{
|
| 43770 |
+
"epoch": 7.120797720797721,
|
| 43771 |
+
"grad_norm": 0.16036351025104523,
|
| 43772 |
+
"learning_rate": 3.7785380172083415e-05,
|
| 43773 |
+
"loss": 0.9017,
|
| 43774 |
+
"step": 6252
|
| 43775 |
+
},
|
| 43776 |
+
{
|
| 43777 |
+
"epoch": 7.121937321937322,
|
| 43778 |
+
"grad_norm": 0.20591062307357788,
|
| 43779 |
+
"learning_rate": 3.778137615849785e-05,
|
| 43780 |
+
"loss": 0.5711,
|
| 43781 |
+
"step": 6253
|
| 43782 |
+
},
|
| 43783 |
+
{
|
| 43784 |
+
"epoch": 7.123076923076923,
|
| 43785 |
+
"grad_norm": 0.19914428889751434,
|
| 43786 |
+
"learning_rate": 3.777737170097993e-05,
|
| 43787 |
+
"loss": 0.7247,
|
| 43788 |
+
"step": 6254
|
| 43789 |
+
},
|
| 43790 |
+
{
|
| 43791 |
+
"epoch": 7.124216524216524,
|
| 43792 |
+
"grad_norm": 0.19862796366214752,
|
| 43793 |
+
"learning_rate": 3.7773366799668776e-05,
|
| 43794 |
+
"loss": 0.8529,
|
| 43795 |
+
"step": 6255
|
| 43796 |
+
},
|
| 43797 |
+
{
|
| 43798 |
+
"epoch": 7.1253561253561255,
|
| 43799 |
+
"grad_norm": 0.1894269585609436,
|
| 43800 |
+
"learning_rate": 3.7769361454703445e-05,
|
| 43801 |
+
"loss": 0.8447,
|
| 43802 |
+
"step": 6256
|
| 43803 |
+
},
|
| 43804 |
+
{
|
| 43805 |
+
"epoch": 7.126495726495726,
|
| 43806 |
+
"grad_norm": 0.21392220258712769,
|
| 43807 |
+
"learning_rate": 3.7765355666223085e-05,
|
| 43808 |
+
"loss": 0.5833,
|
| 43809 |
+
"step": 6257
|
| 43810 |
+
},
|
| 43811 |
+
{
|
| 43812 |
+
"epoch": 7.1276353276353275,
|
| 43813 |
+
"grad_norm": 0.18810603022575378,
|
| 43814 |
+
"learning_rate": 3.7761349434366804e-05,
|
| 43815 |
+
"loss": 0.6764,
|
| 43816 |
+
"step": 6258
|
| 43817 |
+
},
|
| 43818 |
+
{
|
| 43819 |
+
"epoch": 7.128774928774929,
|
| 43820 |
+
"grad_norm": 0.22102965414524078,
|
| 43821 |
+
"learning_rate": 3.775734275927378e-05,
|
| 43822 |
+
"loss": 0.6572,
|
| 43823 |
+
"step": 6259
|
| 43824 |
+
},
|
| 43825 |
+
{
|
| 43826 |
+
"epoch": 7.12991452991453,
|
| 43827 |
+
"grad_norm": 0.18941909074783325,
|
| 43828 |
+
"learning_rate": 3.7753335641083146e-05,
|
| 43829 |
+
"loss": 0.662,
|
| 43830 |
+
"step": 6260
|
| 43831 |
+
},
|
| 43832 |
+
{
|
| 43833 |
+
"epoch": 7.131054131054131,
|
| 43834 |
+
"grad_norm": 0.2360292226076126,
|
| 43835 |
+
"learning_rate": 3.7749328079934104e-05,
|
| 43836 |
+
"loss": 0.4593,
|
| 43837 |
+
"step": 6261
|
| 43838 |
+
},
|
| 43839 |
+
{
|
| 43840 |
+
"epoch": 7.132193732193732,
|
| 43841 |
+
"grad_norm": 0.2077096402645111,
|
| 43842 |
+
"learning_rate": 3.774532007596583e-05,
|
| 43843 |
+
"loss": 0.6786,
|
| 43844 |
+
"step": 6262
|
| 43845 |
+
},
|
| 43846 |
+
{
|
| 43847 |
+
"epoch": 7.133333333333334,
|
| 43848 |
+
"grad_norm": 0.20154207944869995,
|
| 43849 |
+
"learning_rate": 3.774131162931754e-05,
|
| 43850 |
+
"loss": 0.767,
|
| 43851 |
+
"step": 6263
|
| 43852 |
+
},
|
| 43853 |
+
{
|
| 43854 |
+
"epoch": 7.134472934472934,
|
| 43855 |
+
"grad_norm": 0.20883165299892426,
|
| 43856 |
+
"learning_rate": 3.7737302740128466e-05,
|
| 43857 |
+
"loss": 0.7668,
|
| 43858 |
+
"step": 6264
|
| 43859 |
+
},
|
| 43860 |
+
{
|
| 43861 |
+
"epoch": 7.135612535612536,
|
| 43862 |
+
"grad_norm": 0.24615712463855743,
|
| 43863 |
+
"learning_rate": 3.7733293408537835e-05,
|
| 43864 |
+
"loss": 0.5943,
|
| 43865 |
+
"step": 6265
|
| 43866 |
+
},
|
| 43867 |
+
{
|
| 43868 |
+
"epoch": 7.136752136752137,
|
| 43869 |
+
"grad_norm": 0.22391575574874878,
|
| 43870 |
+
"learning_rate": 3.772928363468491e-05,
|
| 43871 |
+
"loss": 0.5849,
|
| 43872 |
+
"step": 6266
|
| 43873 |
+
},
|
| 43874 |
+
{
|
| 43875 |
+
"epoch": 7.137891737891738,
|
| 43876 |
+
"grad_norm": 0.19004112482070923,
|
| 43877 |
+
"learning_rate": 3.7725273418708954e-05,
|
| 43878 |
+
"loss": 0.7521,
|
| 43879 |
+
"step": 6267
|
| 43880 |
+
},
|
| 43881 |
+
{
|
| 43882 |
+
"epoch": 7.139031339031339,
|
| 43883 |
+
"grad_norm": 0.19732090830802917,
|
| 43884 |
+
"learning_rate": 3.772126276074926e-05,
|
| 43885 |
+
"loss": 0.7854,
|
| 43886 |
+
"step": 6268
|
| 43887 |
+
},
|
| 43888 |
+
{
|
| 43889 |
+
"epoch": 7.140170940170941,
|
| 43890 |
+
"grad_norm": 0.2178681492805481,
|
| 43891 |
+
"learning_rate": 3.771725166094512e-05,
|
| 43892 |
+
"loss": 0.5679,
|
| 43893 |
+
"step": 6269
|
| 43894 |
+
},
|
| 43895 |
+
{
|
| 43896 |
+
"epoch": 7.141310541310541,
|
| 43897 |
+
"grad_norm": 0.19348812103271484,
|
| 43898 |
+
"learning_rate": 3.771324011943587e-05,
|
| 43899 |
+
"loss": 0.6625,
|
| 43900 |
+
"step": 6270
|
| 43901 |
+
},
|
| 43902 |
+
{
|
| 43903 |
+
"epoch": 7.1424501424501425,
|
| 43904 |
+
"grad_norm": 0.20072202384471893,
|
| 43905 |
+
"learning_rate": 3.770922813636082e-05,
|
| 43906 |
+
"loss": 0.7176,
|
| 43907 |
+
"step": 6271
|
| 43908 |
+
},
|
| 43909 |
+
{
|
| 43910 |
+
"epoch": 7.143589743589744,
|
| 43911 |
+
"grad_norm": 0.17724600434303284,
|
| 43912 |
+
"learning_rate": 3.770521571185933e-05,
|
| 43913 |
+
"loss": 0.8514,
|
| 43914 |
+
"step": 6272
|
| 43915 |
+
},
|
| 43916 |
+
{
|
| 43917 |
+
"epoch": 7.1447293447293445,
|
| 43918 |
+
"grad_norm": 0.1965605765581131,
|
| 43919 |
+
"learning_rate": 3.770120284607076e-05,
|
| 43920 |
+
"loss": 0.772,
|
| 43921 |
+
"step": 6273
|
| 43922 |
+
},
|
| 43923 |
+
{
|
| 43924 |
+
"epoch": 7.145868945868946,
|
| 43925 |
+
"grad_norm": 0.19905537366867065,
|
| 43926 |
+
"learning_rate": 3.7697189539134484e-05,
|
| 43927 |
+
"loss": 0.6396,
|
| 43928 |
+
"step": 6274
|
| 43929 |
+
},
|
| 43930 |
+
{
|
| 43931 |
+
"epoch": 7.147008547008547,
|
| 43932 |
+
"grad_norm": 0.16375818848609924,
|
| 43933 |
+
"learning_rate": 3.769317579118989e-05,
|
| 43934 |
+
"loss": 0.7937,
|
| 43935 |
+
"step": 6275
|
| 43936 |
+
},
|
| 43937 |
+
{
|
| 43938 |
+
"epoch": 7.148148148148148,
|
| 43939 |
+
"grad_norm": 0.17767931520938873,
|
| 43940 |
+
"learning_rate": 3.768916160237641e-05,
|
| 43941 |
+
"loss": 0.7634,
|
| 43942 |
+
"step": 6276
|
| 43943 |
+
},
|
| 43944 |
+
{
|
| 43945 |
+
"epoch": 7.149287749287749,
|
| 43946 |
+
"grad_norm": 0.2176171839237213,
|
| 43947 |
+
"learning_rate": 3.768514697283345e-05,
|
| 43948 |
+
"loss": 0.6005,
|
| 43949 |
+
"step": 6277
|
| 43950 |
+
},
|
| 43951 |
+
{
|
| 43952 |
+
"epoch": 7.150427350427351,
|
| 43953 |
+
"grad_norm": 0.2047884464263916,
|
| 43954 |
+
"learning_rate": 3.768113190270044e-05,
|
| 43955 |
+
"loss": 0.6384,
|
| 43956 |
+
"step": 6278
|
| 43957 |
+
},
|
| 43958 |
+
{
|
| 43959 |
+
"epoch": 7.151566951566951,
|
| 43960 |
+
"grad_norm": 0.2172878235578537,
|
| 43961 |
+
"learning_rate": 3.767711639211685e-05,
|
| 43962 |
+
"loss": 0.6811,
|
| 43963 |
+
"step": 6279
|
| 43964 |
+
},
|
| 43965 |
+
{
|
| 43966 |
+
"epoch": 7.152706552706553,
|
| 43967 |
+
"grad_norm": 0.22276462614536285,
|
| 43968 |
+
"learning_rate": 3.767310044122215e-05,
|
| 43969 |
+
"loss": 0.7699,
|
| 43970 |
+
"step": 6280
|
| 43971 |
+
},
|
| 43972 |
+
{
|
| 43973 |
+
"epoch": 7.153846153846154,
|
| 43974 |
+
"grad_norm": 0.21287479996681213,
|
| 43975 |
+
"learning_rate": 3.766908405015582e-05,
|
| 43976 |
+
"loss": 0.557,
|
| 43977 |
+
"step": 6281
|
| 43978 |
+
},
|
| 43979 |
+
{
|
| 43980 |
+
"epoch": 7.154985754985755,
|
| 43981 |
+
"grad_norm": 0.16105368733406067,
|
| 43982 |
+
"learning_rate": 3.766506721905735e-05,
|
| 43983 |
+
"loss": 0.8144,
|
| 43984 |
+
"step": 6282
|
| 43985 |
+
},
|
| 43986 |
+
{
|
| 43987 |
+
"epoch": 7.156125356125356,
|
| 43988 |
+
"grad_norm": 0.15614740550518036,
|
| 43989 |
+
"learning_rate": 3.766104994806628e-05,
|
| 43990 |
+
"loss": 0.856,
|
| 43991 |
+
"step": 6283
|
| 43992 |
+
},
|
| 43993 |
+
{
|
| 43994 |
+
"epoch": 7.157264957264958,
|
| 43995 |
+
"grad_norm": 0.22421568632125854,
|
| 43996 |
+
"learning_rate": 3.765703223732212e-05,
|
| 43997 |
+
"loss": 0.7493,
|
| 43998 |
+
"step": 6284
|
| 43999 |
+
},
|
| 44000 |
+
{
|
| 44001 |
+
"epoch": 7.158404558404558,
|
| 44002 |
+
"grad_norm": 0.19010932743549347,
|
| 44003 |
+
"learning_rate": 3.765301408696443e-05,
|
| 44004 |
+
"loss": 0.7169,
|
| 44005 |
+
"step": 6285
|
| 44006 |
+
},
|
| 44007 |
+
{
|
| 44008 |
+
"epoch": 7.15954415954416,
|
| 44009 |
+
"grad_norm": 0.17612417042255402,
|
| 44010 |
+
"learning_rate": 3.7648995497132755e-05,
|
| 44011 |
+
"loss": 1.0025,
|
| 44012 |
+
"step": 6286
|
| 44013 |
+
},
|
| 44014 |
+
{
|
| 44015 |
+
"epoch": 7.160683760683761,
|
| 44016 |
+
"grad_norm": 0.2417812943458557,
|
| 44017 |
+
"learning_rate": 3.76449764679667e-05,
|
| 44018 |
+
"loss": 0.5729,
|
| 44019 |
+
"step": 6287
|
| 44020 |
+
},
|
| 44021 |
+
{
|
| 44022 |
+
"epoch": 7.1618233618233615,
|
| 44023 |
+
"grad_norm": 0.15472744405269623,
|
| 44024 |
+
"learning_rate": 3.7640956999605815e-05,
|
| 44025 |
+
"loss": 0.8218,
|
| 44026 |
+
"step": 6288
|
| 44027 |
+
},
|
| 44028 |
+
{
|
| 44029 |
+
"epoch": 7.162962962962963,
|
| 44030 |
+
"grad_norm": 0.1943567395210266,
|
| 44031 |
+
"learning_rate": 3.763693709218975e-05,
|
| 44032 |
+
"loss": 0.7593,
|
| 44033 |
+
"step": 6289
|
| 44034 |
+
},
|
| 44035 |
+
{
|
| 44036 |
+
"epoch": 7.164102564102564,
|
| 44037 |
+
"grad_norm": 0.2067941129207611,
|
| 44038 |
+
"learning_rate": 3.7632916745858095e-05,
|
| 44039 |
+
"loss": 0.5406,
|
| 44040 |
+
"step": 6290
|
| 44041 |
+
},
|
| 44042 |
+
{
|
| 44043 |
+
"epoch": 7.165242165242165,
|
| 44044 |
+
"grad_norm": 0.1726512312889099,
|
| 44045 |
+
"learning_rate": 3.76288959607505e-05,
|
| 44046 |
+
"loss": 0.7521,
|
| 44047 |
+
"step": 6291
|
| 44048 |
+
},
|
| 44049 |
+
{
|
| 44050 |
+
"epoch": 7.166381766381766,
|
| 44051 |
+
"grad_norm": 0.18153612315654755,
|
| 44052 |
+
"learning_rate": 3.7624874737006635e-05,
|
| 44053 |
+
"loss": 0.6399,
|
| 44054 |
+
"step": 6292
|
| 44055 |
+
},
|
| 44056 |
+
{
|
| 44057 |
+
"epoch": 7.167521367521368,
|
| 44058 |
+
"grad_norm": 0.1801934391260147,
|
| 44059 |
+
"learning_rate": 3.762085307476614e-05,
|
| 44060 |
+
"loss": 0.7035,
|
| 44061 |
+
"step": 6293
|
| 44062 |
+
},
|
| 44063 |
+
{
|
| 44064 |
+
"epoch": 7.168660968660968,
|
| 44065 |
+
"grad_norm": 0.2601912319660187,
|
| 44066 |
+
"learning_rate": 3.761683097416871e-05,
|
| 44067 |
+
"loss": 0.612,
|
| 44068 |
+
"step": 6294
|
| 44069 |
+
},
|
| 44070 |
+
{
|
| 44071 |
+
"epoch": 7.16980056980057,
|
| 44072 |
+
"grad_norm": 0.20805248618125916,
|
| 44073 |
+
"learning_rate": 3.761280843535404e-05,
|
| 44074 |
+
"loss": 0.7866,
|
| 44075 |
+
"step": 6295
|
| 44076 |
+
},
|
| 44077 |
+
{
|
| 44078 |
+
"epoch": 7.170940170940171,
|
| 44079 |
+
"grad_norm": 0.2429533451795578,
|
| 44080 |
+
"learning_rate": 3.760878545846186e-05,
|
| 44081 |
+
"loss": 0.5853,
|
| 44082 |
+
"step": 6296
|
| 44083 |
+
},
|
| 44084 |
+
{
|
| 44085 |
+
"epoch": 7.172079772079772,
|
| 44086 |
+
"grad_norm": 0.17130783200263977,
|
| 44087 |
+
"learning_rate": 3.760476204363187e-05,
|
| 44088 |
+
"loss": 0.8799,
|
| 44089 |
+
"step": 6297
|
| 44090 |
+
},
|
| 44091 |
+
{
|
| 44092 |
+
"epoch": 7.173219373219373,
|
| 44093 |
+
"grad_norm": 0.15848739445209503,
|
| 44094 |
+
"learning_rate": 3.760073819100384e-05,
|
| 44095 |
+
"loss": 0.9686,
|
| 44096 |
+
"step": 6298
|
| 44097 |
+
},
|
| 44098 |
+
{
|
| 44099 |
+
"epoch": 7.174358974358975,
|
| 44100 |
+
"grad_norm": 0.18064692616462708,
|
| 44101 |
+
"learning_rate": 3.7596713900717524e-05,
|
| 44102 |
+
"loss": 0.6252,
|
| 44103 |
+
"step": 6299
|
| 44104 |
+
},
|
| 44105 |
+
{
|
| 44106 |
+
"epoch": 7.175498575498575,
|
| 44107 |
+
"grad_norm": 0.17840689420700073,
|
| 44108 |
+
"learning_rate": 3.7592689172912696e-05,
|
| 44109 |
+
"loss": 0.8896,
|
| 44110 |
+
"step": 6300
|
| 44111 |
}
|
| 44112 |
],
|
| 44113 |
"logging_steps": 1,
|
|
|
|
| 44127 |
"attributes": {}
|
| 44128 |
}
|
| 44129 |
},
|
| 44130 |
+
"total_flos": 3.5225081021825925e+19,
|
| 44131 |
"train_batch_size": 8,
|
| 44132 |
"trial_name": null,
|
| 44133 |
"trial_params": null
|