End of training
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: transformers
|
|
| 3 |
license: other
|
| 4 |
base_model: facebook/mask2former-swin-base-IN21k-ade-semantic
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: mask2former-finetuned-ER-Mito-LD3
|
|
@@ -14,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# mask2former-finetuned-ER-Mito-LD3
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/mask2former-swin-base-IN21k-ade-semantic](https://huggingface.co/facebook/mask2former-swin-base-IN21k-ade-semantic) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 33.
|
| 20 |
- Dummy: 1.0
|
| 21 |
|
| 22 |
## Model description
|
|
|
|
| 3 |
license: other
|
| 4 |
base_model: facebook/mask2former-swin-base-IN21k-ade-semantic
|
| 5 |
tags:
|
| 6 |
+
- image-segmentation
|
| 7 |
+
- vision
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: mask2former-finetuned-ER-Mito-LD3
|
|
|
|
| 16 |
|
| 17 |
# mask2former-finetuned-ER-Mito-LD3
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/mask2former-swin-base-IN21k-ade-semantic](https://huggingface.co/facebook/mask2former-swin-base-IN21k-ade-semantic) on the Dnq2025/Mask2former_Pretrain dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 33.5405
|
| 22 |
- Dummy: 1.0
|
| 23 |
|
| 24 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 124.03846153846153,
|
| 3 |
+
"eval_dummy": 1.0,
|
| 4 |
+
"eval_loss": 33.54045104980469,
|
| 5 |
+
"eval_runtime": 18.5302,
|
| 6 |
+
"eval_samples_per_second": 2.59,
|
| 7 |
+
"eval_steps_per_second": 0.54,
|
| 8 |
+
"total_flos": 1.8148731642810335e+19,
|
| 9 |
+
"train_loss": 14.019830729166667,
|
| 10 |
+
"train_runtime": 31415.0856,
|
| 11 |
+
"train_samples_per_second": 2.053,
|
| 12 |
+
"train_steps_per_second": 0.411
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 124.03846153846153,
|
| 3 |
+
"eval_dummy": 1.0,
|
| 4 |
+
"eval_loss": 33.54045104980469,
|
| 5 |
+
"eval_runtime": 18.5302,
|
| 6 |
+
"eval_samples_per_second": 2.59,
|
| 7 |
+
"eval_steps_per_second": 0.54
|
| 8 |
+
}
|
runs/Mar26_09-40-29_cdr2595.int.cedar.computecanada.ca/events.out.tfevents.1743038762.cdr2595.int.cedar.computecanada.ca.1212142.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2154c5132a221c72df5d2b1a44d774d65971905a8e73782f9d56a00c16646506
|
| 3 |
+
size 408
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 124.03846153846153,
|
| 3 |
+
"total_flos": 1.8148731642810335e+19,
|
| 4 |
+
"train_loss": 14.019830729166667,
|
| 5 |
+
"train_runtime": 31415.0856,
|
| 6 |
+
"train_samples_per_second": 2.053,
|
| 7 |
+
"train_steps_per_second": 0.411
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2071 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 124.03846153846153,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 12900,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.9615384615384616,
|
| 14 |
+
"grad_norm": 165.56590270996094,
|
| 15 |
+
"learning_rate": 9.922558139534884e-05,
|
| 16 |
+
"loss": 48.5372,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_dummy": 1.0,
|
| 22 |
+
"eval_loss": 36.333778381347656,
|
| 23 |
+
"eval_runtime": 21.9927,
|
| 24 |
+
"eval_samples_per_second": 2.183,
|
| 25 |
+
"eval_steps_per_second": 0.455,
|
| 26 |
+
"step": 104
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.9230769230769231,
|
| 30 |
+
"grad_norm": 143.93603515625,
|
| 31 |
+
"learning_rate": 9.845116279069768e-05,
|
| 32 |
+
"loss": 33.5327,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_dummy": 1.0,
|
| 38 |
+
"eval_loss": 31.735132217407227,
|
| 39 |
+
"eval_runtime": 16.9414,
|
| 40 |
+
"eval_samples_per_second": 2.833,
|
| 41 |
+
"eval_steps_per_second": 0.59,
|
| 42 |
+
"step": 208
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.8846153846153846,
|
| 46 |
+
"grad_norm": 135.81661987304688,
|
| 47 |
+
"learning_rate": 9.767674418604652e-05,
|
| 48 |
+
"loss": 29.7691,
|
| 49 |
+
"step": 300
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"eval_dummy": 1.0,
|
| 54 |
+
"eval_loss": 30.485803604125977,
|
| 55 |
+
"eval_runtime": 16.7561,
|
| 56 |
+
"eval_samples_per_second": 2.865,
|
| 57 |
+
"eval_steps_per_second": 0.597,
|
| 58 |
+
"step": 312
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 3.8461538461538463,
|
| 62 |
+
"grad_norm": 110.2176284790039,
|
| 63 |
+
"learning_rate": 9.690232558139534e-05,
|
| 64 |
+
"loss": 26.3002,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.0,
|
| 69 |
+
"eval_dummy": 1.0,
|
| 70 |
+
"eval_loss": 28.60906219482422,
|
| 71 |
+
"eval_runtime": 16.9439,
|
| 72 |
+
"eval_samples_per_second": 2.833,
|
| 73 |
+
"eval_steps_per_second": 0.59,
|
| 74 |
+
"step": 416
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.8076923076923075,
|
| 78 |
+
"grad_norm": 112.39118194580078,
|
| 79 |
+
"learning_rate": 9.612790697674419e-05,
|
| 80 |
+
"loss": 24.7501,
|
| 81 |
+
"step": 500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.0,
|
| 85 |
+
"eval_dummy": 1.0,
|
| 86 |
+
"eval_loss": 27.096742630004883,
|
| 87 |
+
"eval_runtime": 16.7521,
|
| 88 |
+
"eval_samples_per_second": 2.865,
|
| 89 |
+
"eval_steps_per_second": 0.597,
|
| 90 |
+
"step": 520
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.769230769230769,
|
| 94 |
+
"grad_norm": 86.3100357055664,
|
| 95 |
+
"learning_rate": 9.535348837209303e-05,
|
| 96 |
+
"loss": 23.4495,
|
| 97 |
+
"step": 600
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 6.0,
|
| 101 |
+
"eval_dummy": 1.0,
|
| 102 |
+
"eval_loss": 26.624135971069336,
|
| 103 |
+
"eval_runtime": 16.6013,
|
| 104 |
+
"eval_samples_per_second": 2.891,
|
| 105 |
+
"eval_steps_per_second": 0.602,
|
| 106 |
+
"step": 624
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 6.730769230769231,
|
| 110 |
+
"grad_norm": 58.464332580566406,
|
| 111 |
+
"learning_rate": 9.457906976744187e-05,
|
| 112 |
+
"loss": 23.274,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 7.0,
|
| 117 |
+
"eval_dummy": 1.0,
|
| 118 |
+
"eval_loss": 27.154443740844727,
|
| 119 |
+
"eval_runtime": 17.6955,
|
| 120 |
+
"eval_samples_per_second": 2.713,
|
| 121 |
+
"eval_steps_per_second": 0.565,
|
| 122 |
+
"step": 728
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.6923076923076925,
|
| 126 |
+
"grad_norm": 42.398406982421875,
|
| 127 |
+
"learning_rate": 9.38046511627907e-05,
|
| 128 |
+
"loss": 21.1617,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 8.0,
|
| 133 |
+
"eval_dummy": 1.0,
|
| 134 |
+
"eval_loss": 27.462488174438477,
|
| 135 |
+
"eval_runtime": 16.2589,
|
| 136 |
+
"eval_samples_per_second": 2.952,
|
| 137 |
+
"eval_steps_per_second": 0.615,
|
| 138 |
+
"step": 832
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 8.653846153846153,
|
| 142 |
+
"grad_norm": 69.99388122558594,
|
| 143 |
+
"learning_rate": 9.303023255813954e-05,
|
| 144 |
+
"loss": 20.373,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 9.0,
|
| 149 |
+
"eval_dummy": 1.0,
|
| 150 |
+
"eval_loss": 27.574462890625,
|
| 151 |
+
"eval_runtime": 17.0559,
|
| 152 |
+
"eval_samples_per_second": 2.814,
|
| 153 |
+
"eval_steps_per_second": 0.586,
|
| 154 |
+
"step": 936
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 9.615384615384615,
|
| 158 |
+
"grad_norm": 51.642242431640625,
|
| 159 |
+
"learning_rate": 9.225581395348837e-05,
|
| 160 |
+
"loss": 20.4295,
|
| 161 |
+
"step": 1000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 10.0,
|
| 165 |
+
"eval_dummy": 1.0,
|
| 166 |
+
"eval_loss": 27.69423484802246,
|
| 167 |
+
"eval_runtime": 16.3331,
|
| 168 |
+
"eval_samples_per_second": 2.939,
|
| 169 |
+
"eval_steps_per_second": 0.612,
|
| 170 |
+
"step": 1040
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 10.576923076923077,
|
| 174 |
+
"grad_norm": 39.88796615600586,
|
| 175 |
+
"learning_rate": 9.14813953488372e-05,
|
| 176 |
+
"loss": 20.2526,
|
| 177 |
+
"step": 1100
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 11.0,
|
| 181 |
+
"eval_dummy": 1.0,
|
| 182 |
+
"eval_loss": 27.782920837402344,
|
| 183 |
+
"eval_runtime": 16.9662,
|
| 184 |
+
"eval_samples_per_second": 2.829,
|
| 185 |
+
"eval_steps_per_second": 0.589,
|
| 186 |
+
"step": 1144
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 11.538461538461538,
|
| 190 |
+
"grad_norm": 50.71794509887695,
|
| 191 |
+
"learning_rate": 9.070697674418606e-05,
|
| 192 |
+
"loss": 19.2572,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 12.0,
|
| 197 |
+
"eval_dummy": 1.0,
|
| 198 |
+
"eval_loss": 27.295957565307617,
|
| 199 |
+
"eval_runtime": 16.7472,
|
| 200 |
+
"eval_samples_per_second": 2.866,
|
| 201 |
+
"eval_steps_per_second": 0.597,
|
| 202 |
+
"step": 1248
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 12.5,
|
| 206 |
+
"grad_norm": 45.02073669433594,
|
| 207 |
+
"learning_rate": 8.99325581395349e-05,
|
| 208 |
+
"loss": 19.0089,
|
| 209 |
+
"step": 1300
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 13.0,
|
| 213 |
+
"eval_dummy": 1.0,
|
| 214 |
+
"eval_loss": 26.0039005279541,
|
| 215 |
+
"eval_runtime": 16.8217,
|
| 216 |
+
"eval_samples_per_second": 2.853,
|
| 217 |
+
"eval_steps_per_second": 0.594,
|
| 218 |
+
"step": 1352
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 13.461538461538462,
|
| 222 |
+
"grad_norm": 33.62112808227539,
|
| 223 |
+
"learning_rate": 8.915813953488373e-05,
|
| 224 |
+
"loss": 18.3621,
|
| 225 |
+
"step": 1400
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 14.0,
|
| 229 |
+
"eval_dummy": 1.0,
|
| 230 |
+
"eval_loss": 26.562255859375,
|
| 231 |
+
"eval_runtime": 16.6581,
|
| 232 |
+
"eval_samples_per_second": 2.881,
|
| 233 |
+
"eval_steps_per_second": 0.6,
|
| 234 |
+
"step": 1456
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 14.423076923076923,
|
| 238 |
+
"grad_norm": 44.2991943359375,
|
| 239 |
+
"learning_rate": 8.838372093023257e-05,
|
| 240 |
+
"loss": 18.0517,
|
| 241 |
+
"step": 1500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 15.0,
|
| 245 |
+
"eval_dummy": 1.0,
|
| 246 |
+
"eval_loss": 26.27000617980957,
|
| 247 |
+
"eval_runtime": 17.496,
|
| 248 |
+
"eval_samples_per_second": 2.743,
|
| 249 |
+
"eval_steps_per_second": 0.572,
|
| 250 |
+
"step": 1560
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 15.384615384615385,
|
| 254 |
+
"grad_norm": 44.68825912475586,
|
| 255 |
+
"learning_rate": 8.76093023255814e-05,
|
| 256 |
+
"loss": 18.3139,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 16.0,
|
| 261 |
+
"eval_dummy": 1.0,
|
| 262 |
+
"eval_loss": 27.297170639038086,
|
| 263 |
+
"eval_runtime": 16.2819,
|
| 264 |
+
"eval_samples_per_second": 2.948,
|
| 265 |
+
"eval_steps_per_second": 0.614,
|
| 266 |
+
"step": 1664
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 16.346153846153847,
|
| 270 |
+
"grad_norm": 50.15152359008789,
|
| 271 |
+
"learning_rate": 8.683488372093023e-05,
|
| 272 |
+
"loss": 17.6129,
|
| 273 |
+
"step": 1700
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 17.0,
|
| 277 |
+
"eval_dummy": 1.0,
|
| 278 |
+
"eval_loss": 26.486886978149414,
|
| 279 |
+
"eval_runtime": 17.6532,
|
| 280 |
+
"eval_samples_per_second": 2.719,
|
| 281 |
+
"eval_steps_per_second": 0.566,
|
| 282 |
+
"step": 1768
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 17.307692307692307,
|
| 286 |
+
"grad_norm": 31.138574600219727,
|
| 287 |
+
"learning_rate": 8.606046511627907e-05,
|
| 288 |
+
"loss": 17.8402,
|
| 289 |
+
"step": 1800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 18.0,
|
| 293 |
+
"eval_dummy": 1.0,
|
| 294 |
+
"eval_loss": 27.761808395385742,
|
| 295 |
+
"eval_runtime": 16.6098,
|
| 296 |
+
"eval_samples_per_second": 2.89,
|
| 297 |
+
"eval_steps_per_second": 0.602,
|
| 298 |
+
"step": 1872
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 18.26923076923077,
|
| 302 |
+
"grad_norm": 45.22633361816406,
|
| 303 |
+
"learning_rate": 8.52860465116279e-05,
|
| 304 |
+
"loss": 16.6494,
|
| 305 |
+
"step": 1900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 19.0,
|
| 309 |
+
"eval_dummy": 1.0,
|
| 310 |
+
"eval_loss": 27.517309188842773,
|
| 311 |
+
"eval_runtime": 16.9988,
|
| 312 |
+
"eval_samples_per_second": 2.824,
|
| 313 |
+
"eval_steps_per_second": 0.588,
|
| 314 |
+
"step": 1976
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 19.23076923076923,
|
| 318 |
+
"grad_norm": 25.58769989013672,
|
| 319 |
+
"learning_rate": 8.451162790697674e-05,
|
| 320 |
+
"loss": 17.0833,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 20.0,
|
| 325 |
+
"eval_dummy": 1.0,
|
| 326 |
+
"eval_loss": 28.124242782592773,
|
| 327 |
+
"eval_runtime": 16.6787,
|
| 328 |
+
"eval_samples_per_second": 2.878,
|
| 329 |
+
"eval_steps_per_second": 0.6,
|
| 330 |
+
"step": 2080
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 20.192307692307693,
|
| 334 |
+
"grad_norm": 30.538772583007812,
|
| 335 |
+
"learning_rate": 8.373720930232558e-05,
|
| 336 |
+
"loss": 16.5967,
|
| 337 |
+
"step": 2100
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 21.0,
|
| 341 |
+
"eval_dummy": 1.0,
|
| 342 |
+
"eval_loss": 29.119504928588867,
|
| 343 |
+
"eval_runtime": 16.9877,
|
| 344 |
+
"eval_samples_per_second": 2.826,
|
| 345 |
+
"eval_steps_per_second": 0.589,
|
| 346 |
+
"step": 2184
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 21.153846153846153,
|
| 350 |
+
"grad_norm": 34.11674499511719,
|
| 351 |
+
"learning_rate": 8.296279069767443e-05,
|
| 352 |
+
"loss": 16.2634,
|
| 353 |
+
"step": 2200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 22.0,
|
| 357 |
+
"eval_dummy": 1.0,
|
| 358 |
+
"eval_loss": 27.036653518676758,
|
| 359 |
+
"eval_runtime": 16.3157,
|
| 360 |
+
"eval_samples_per_second": 2.942,
|
| 361 |
+
"eval_steps_per_second": 0.613,
|
| 362 |
+
"step": 2288
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 22.115384615384617,
|
| 366 |
+
"grad_norm": 23.20075798034668,
|
| 367 |
+
"learning_rate": 8.218837209302326e-05,
|
| 368 |
+
"loss": 16.6797,
|
| 369 |
+
"step": 2300
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 23.0,
|
| 373 |
+
"eval_dummy": 1.0,
|
| 374 |
+
"eval_loss": 27.179914474487305,
|
| 375 |
+
"eval_runtime": 17.6647,
|
| 376 |
+
"eval_samples_per_second": 2.717,
|
| 377 |
+
"eval_steps_per_second": 0.566,
|
| 378 |
+
"step": 2392
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 23.076923076923077,
|
| 382 |
+
"grad_norm": 38.62594223022461,
|
| 383 |
+
"learning_rate": 8.14139534883721e-05,
|
| 384 |
+
"loss": 16.0344,
|
| 385 |
+
"step": 2400
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 24.0,
|
| 389 |
+
"eval_dummy": 1.0,
|
| 390 |
+
"eval_loss": 26.640764236450195,
|
| 391 |
+
"eval_runtime": 17.4121,
|
| 392 |
+
"eval_samples_per_second": 2.757,
|
| 393 |
+
"eval_steps_per_second": 0.574,
|
| 394 |
+
"step": 2496
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 24.03846153846154,
|
| 398 |
+
"grad_norm": 25.629343032836914,
|
| 399 |
+
"learning_rate": 8.063953488372093e-05,
|
| 400 |
+
"loss": 15.8706,
|
| 401 |
+
"step": 2500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 25.0,
|
| 405 |
+
"grad_norm": 108.9260482788086,
|
| 406 |
+
"learning_rate": 7.986511627906977e-05,
|
| 407 |
+
"loss": 15.7701,
|
| 408 |
+
"step": 2600
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 25.0,
|
| 412 |
+
"eval_dummy": 1.0,
|
| 413 |
+
"eval_loss": 28.403966903686523,
|
| 414 |
+
"eval_runtime": 16.6389,
|
| 415 |
+
"eval_samples_per_second": 2.885,
|
| 416 |
+
"eval_steps_per_second": 0.601,
|
| 417 |
+
"step": 2600
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 25.96153846153846,
|
| 421 |
+
"grad_norm": 39.876651763916016,
|
| 422 |
+
"learning_rate": 7.90906976744186e-05,
|
| 423 |
+
"loss": 15.6061,
|
| 424 |
+
"step": 2700
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 26.0,
|
| 428 |
+
"eval_dummy": 1.0,
|
| 429 |
+
"eval_loss": 28.06866455078125,
|
| 430 |
+
"eval_runtime": 17.057,
|
| 431 |
+
"eval_samples_per_second": 2.814,
|
| 432 |
+
"eval_steps_per_second": 0.586,
|
| 433 |
+
"step": 2704
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 26.923076923076923,
|
| 437 |
+
"grad_norm": 24.31376838684082,
|
| 438 |
+
"learning_rate": 7.831627906976746e-05,
|
| 439 |
+
"loss": 15.3311,
|
| 440 |
+
"step": 2800
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 27.0,
|
| 444 |
+
"eval_dummy": 1.0,
|
| 445 |
+
"eval_loss": 27.17653465270996,
|
| 446 |
+
"eval_runtime": 16.4838,
|
| 447 |
+
"eval_samples_per_second": 2.912,
|
| 448 |
+
"eval_steps_per_second": 0.607,
|
| 449 |
+
"step": 2808
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 27.884615384615383,
|
| 453 |
+
"grad_norm": 21.51975440979004,
|
| 454 |
+
"learning_rate": 7.754186046511628e-05,
|
| 455 |
+
"loss": 15.2464,
|
| 456 |
+
"step": 2900
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 28.0,
|
| 460 |
+
"eval_dummy": 1.0,
|
| 461 |
+
"eval_loss": 28.20502471923828,
|
| 462 |
+
"eval_runtime": 17.0908,
|
| 463 |
+
"eval_samples_per_second": 2.809,
|
| 464 |
+
"eval_steps_per_second": 0.585,
|
| 465 |
+
"step": 2912
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 28.846153846153847,
|
| 469 |
+
"grad_norm": 25.89150047302246,
|
| 470 |
+
"learning_rate": 7.676744186046512e-05,
|
| 471 |
+
"loss": 15.0459,
|
| 472 |
+
"step": 3000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 29.0,
|
| 476 |
+
"eval_dummy": 1.0,
|
| 477 |
+
"eval_loss": 28.629125595092773,
|
| 478 |
+
"eval_runtime": 17.0746,
|
| 479 |
+
"eval_samples_per_second": 2.811,
|
| 480 |
+
"eval_steps_per_second": 0.586,
|
| 481 |
+
"step": 3016
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 29.807692307692307,
|
| 485 |
+
"grad_norm": 24.885116577148438,
|
| 486 |
+
"learning_rate": 7.599302325581396e-05,
|
| 487 |
+
"loss": 14.7514,
|
| 488 |
+
"step": 3100
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 30.0,
|
| 492 |
+
"eval_dummy": 1.0,
|
| 493 |
+
"eval_loss": 27.824087142944336,
|
| 494 |
+
"eval_runtime": 16.6658,
|
| 495 |
+
"eval_samples_per_second": 2.88,
|
| 496 |
+
"eval_steps_per_second": 0.6,
|
| 497 |
+
"step": 3120
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 30.76923076923077,
|
| 501 |
+
"grad_norm": 23.02336883544922,
|
| 502 |
+
"learning_rate": 7.52186046511628e-05,
|
| 503 |
+
"loss": 15.0833,
|
| 504 |
+
"step": 3200
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 31.0,
|
| 508 |
+
"eval_dummy": 1.0,
|
| 509 |
+
"eval_loss": 29.19361686706543,
|
| 510 |
+
"eval_runtime": 19.4392,
|
| 511 |
+
"eval_samples_per_second": 2.469,
|
| 512 |
+
"eval_steps_per_second": 0.514,
|
| 513 |
+
"step": 3224
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 31.73076923076923,
|
| 517 |
+
"grad_norm": 24.152498245239258,
|
| 518 |
+
"learning_rate": 7.444418604651163e-05,
|
| 519 |
+
"loss": 15.0817,
|
| 520 |
+
"step": 3300
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 32.0,
|
| 524 |
+
"eval_dummy": 1.0,
|
| 525 |
+
"eval_loss": 28.40435218811035,
|
| 526 |
+
"eval_runtime": 16.6685,
|
| 527 |
+
"eval_samples_per_second": 2.88,
|
| 528 |
+
"eval_steps_per_second": 0.6,
|
| 529 |
+
"step": 3328
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 32.69230769230769,
|
| 533 |
+
"grad_norm": 20.687313079833984,
|
| 534 |
+
"learning_rate": 7.366976744186047e-05,
|
| 535 |
+
"loss": 14.3201,
|
| 536 |
+
"step": 3400
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 33.0,
|
| 540 |
+
"eval_dummy": 1.0,
|
| 541 |
+
"eval_loss": 28.370887756347656,
|
| 542 |
+
"eval_runtime": 16.9055,
|
| 543 |
+
"eval_samples_per_second": 2.839,
|
| 544 |
+
"eval_steps_per_second": 0.592,
|
| 545 |
+
"step": 3432
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 33.65384615384615,
|
| 549 |
+
"grad_norm": 18.918672561645508,
|
| 550 |
+
"learning_rate": 7.289534883720931e-05,
|
| 551 |
+
"loss": 14.5918,
|
| 552 |
+
"step": 3500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 34.0,
|
| 556 |
+
"eval_dummy": 1.0,
|
| 557 |
+
"eval_loss": 29.38982582092285,
|
| 558 |
+
"eval_runtime": 17.1503,
|
| 559 |
+
"eval_samples_per_second": 2.799,
|
| 560 |
+
"eval_steps_per_second": 0.583,
|
| 561 |
+
"step": 3536
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 34.61538461538461,
|
| 565 |
+
"grad_norm": 34.329986572265625,
|
| 566 |
+
"learning_rate": 7.212093023255815e-05,
|
| 567 |
+
"loss": 14.7177,
|
| 568 |
+
"step": 3600
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 35.0,
|
| 572 |
+
"eval_dummy": 1.0,
|
| 573 |
+
"eval_loss": 28.512975692749023,
|
| 574 |
+
"eval_runtime": 17.026,
|
| 575 |
+
"eval_samples_per_second": 2.819,
|
| 576 |
+
"eval_steps_per_second": 0.587,
|
| 577 |
+
"step": 3640
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 35.57692307692308,
|
| 581 |
+
"grad_norm": 14.776827812194824,
|
| 582 |
+
"learning_rate": 7.134651162790697e-05,
|
| 583 |
+
"loss": 13.9919,
|
| 584 |
+
"step": 3700
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 36.0,
|
| 588 |
+
"eval_dummy": 1.0,
|
| 589 |
+
"eval_loss": 27.759668350219727,
|
| 590 |
+
"eval_runtime": 16.7517,
|
| 591 |
+
"eval_samples_per_second": 2.865,
|
| 592 |
+
"eval_steps_per_second": 0.597,
|
| 593 |
+
"step": 3744
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 36.53846153846154,
|
| 597 |
+
"grad_norm": 33.82184982299805,
|
| 598 |
+
"learning_rate": 7.057209302325581e-05,
|
| 599 |
+
"loss": 14.2267,
|
| 600 |
+
"step": 3800
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 37.0,
|
| 604 |
+
"eval_dummy": 1.0,
|
| 605 |
+
"eval_loss": 29.232383728027344,
|
| 606 |
+
"eval_runtime": 16.949,
|
| 607 |
+
"eval_samples_per_second": 2.832,
|
| 608 |
+
"eval_steps_per_second": 0.59,
|
| 609 |
+
"step": 3848
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 37.5,
|
| 613 |
+
"grad_norm": 71.82172393798828,
|
| 614 |
+
"learning_rate": 6.979767441860466e-05,
|
| 615 |
+
"loss": 13.7801,
|
| 616 |
+
"step": 3900
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 38.0,
|
| 620 |
+
"eval_dummy": 1.0,
|
| 621 |
+
"eval_loss": 28.357421875,
|
| 622 |
+
"eval_runtime": 16.6259,
|
| 623 |
+
"eval_samples_per_second": 2.887,
|
| 624 |
+
"eval_steps_per_second": 0.601,
|
| 625 |
+
"step": 3952
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 38.46153846153846,
|
| 629 |
+
"grad_norm": 24.108745574951172,
|
| 630 |
+
"learning_rate": 6.90232558139535e-05,
|
| 631 |
+
"loss": 14.1839,
|
| 632 |
+
"step": 4000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 39.0,
|
| 636 |
+
"eval_dummy": 1.0,
|
| 637 |
+
"eval_loss": 28.8710994720459,
|
| 638 |
+
"eval_runtime": 16.7167,
|
| 639 |
+
"eval_samples_per_second": 2.871,
|
| 640 |
+
"eval_steps_per_second": 0.598,
|
| 641 |
+
"step": 4056
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 39.42307692307692,
|
| 645 |
+
"grad_norm": 24.0490665435791,
|
| 646 |
+
"learning_rate": 6.824883720930233e-05,
|
| 647 |
+
"loss": 13.7545,
|
| 648 |
+
"step": 4100
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 40.0,
|
| 652 |
+
"eval_dummy": 1.0,
|
| 653 |
+
"eval_loss": 28.294702529907227,
|
| 654 |
+
"eval_runtime": 16.5809,
|
| 655 |
+
"eval_samples_per_second": 2.895,
|
| 656 |
+
"eval_steps_per_second": 0.603,
|
| 657 |
+
"step": 4160
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 40.38461538461539,
|
| 661 |
+
"grad_norm": 17.7755184173584,
|
| 662 |
+
"learning_rate": 6.747441860465117e-05,
|
| 663 |
+
"loss": 14.1627,
|
| 664 |
+
"step": 4200
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 41.0,
|
| 668 |
+
"eval_dummy": 1.0,
|
| 669 |
+
"eval_loss": 29.48655128479004,
|
| 670 |
+
"eval_runtime": 16.9288,
|
| 671 |
+
"eval_samples_per_second": 2.835,
|
| 672 |
+
"eval_steps_per_second": 0.591,
|
| 673 |
+
"step": 4264
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 41.34615384615385,
|
| 677 |
+
"grad_norm": 25.07582664489746,
|
| 678 |
+
"learning_rate": 6.670000000000001e-05,
|
| 679 |
+
"loss": 13.5155,
|
| 680 |
+
"step": 4300
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 42.0,
|
| 684 |
+
"eval_dummy": 1.0,
|
| 685 |
+
"eval_loss": 29.852659225463867,
|
| 686 |
+
"eval_runtime": 16.5485,
|
| 687 |
+
"eval_samples_per_second": 2.901,
|
| 688 |
+
"eval_steps_per_second": 0.604,
|
| 689 |
+
"step": 4368
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 42.30769230769231,
|
| 693 |
+
"grad_norm": 35.709686279296875,
|
| 694 |
+
"learning_rate": 6.592558139534885e-05,
|
| 695 |
+
"loss": 13.704,
|
| 696 |
+
"step": 4400
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 43.0,
|
| 700 |
+
"eval_dummy": 1.0,
|
| 701 |
+
"eval_loss": 29.4291934967041,
|
| 702 |
+
"eval_runtime": 16.8607,
|
| 703 |
+
"eval_samples_per_second": 2.847,
|
| 704 |
+
"eval_steps_per_second": 0.593,
|
| 705 |
+
"step": 4472
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 43.26923076923077,
|
| 709 |
+
"grad_norm": 21.939144134521484,
|
| 710 |
+
"learning_rate": 6.515116279069768e-05,
|
| 711 |
+
"loss": 13.6644,
|
| 712 |
+
"step": 4500
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 44.0,
|
| 716 |
+
"eval_dummy": 1.0,
|
| 717 |
+
"eval_loss": 29.23241424560547,
|
| 718 |
+
"eval_runtime": 16.6868,
|
| 719 |
+
"eval_samples_per_second": 2.877,
|
| 720 |
+
"eval_steps_per_second": 0.599,
|
| 721 |
+
"step": 4576
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 44.23076923076923,
|
| 725 |
+
"grad_norm": 22.5328426361084,
|
| 726 |
+
"learning_rate": 6.437674418604652e-05,
|
| 727 |
+
"loss": 13.2006,
|
| 728 |
+
"step": 4600
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 45.0,
|
| 732 |
+
"eval_dummy": 1.0,
|
| 733 |
+
"eval_loss": 29.541372299194336,
|
| 734 |
+
"eval_runtime": 16.3804,
|
| 735 |
+
"eval_samples_per_second": 2.93,
|
| 736 |
+
"eval_steps_per_second": 0.61,
|
| 737 |
+
"step": 4680
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 45.19230769230769,
|
| 741 |
+
"grad_norm": 19.775171279907227,
|
| 742 |
+
"learning_rate": 6.360232558139536e-05,
|
| 743 |
+
"loss": 13.1545,
|
| 744 |
+
"step": 4700
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 46.0,
|
| 748 |
+
"eval_dummy": 1.0,
|
| 749 |
+
"eval_loss": 29.698814392089844,
|
| 750 |
+
"eval_runtime": 17.0544,
|
| 751 |
+
"eval_samples_per_second": 2.815,
|
| 752 |
+
"eval_steps_per_second": 0.586,
|
| 753 |
+
"step": 4784
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 46.15384615384615,
|
| 757 |
+
"grad_norm": 23.579957962036133,
|
| 758 |
+
"learning_rate": 6.28279069767442e-05,
|
| 759 |
+
"loss": 13.5744,
|
| 760 |
+
"step": 4800
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 47.0,
|
| 764 |
+
"eval_dummy": 1.0,
|
| 765 |
+
"eval_loss": 28.993318557739258,
|
| 766 |
+
"eval_runtime": 16.712,
|
| 767 |
+
"eval_samples_per_second": 2.872,
|
| 768 |
+
"eval_steps_per_second": 0.598,
|
| 769 |
+
"step": 4888
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 47.11538461538461,
|
| 773 |
+
"grad_norm": 16.147850036621094,
|
| 774 |
+
"learning_rate": 6.205348837209302e-05,
|
| 775 |
+
"loss": 12.8073,
|
| 776 |
+
"step": 4900
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 48.0,
|
| 780 |
+
"eval_dummy": 1.0,
|
| 781 |
+
"eval_loss": 28.976961135864258,
|
| 782 |
+
"eval_runtime": 17.0515,
|
| 783 |
+
"eval_samples_per_second": 2.815,
|
| 784 |
+
"eval_steps_per_second": 0.586,
|
| 785 |
+
"step": 4992
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 48.07692307692308,
|
| 789 |
+
"grad_norm": 39.781028747558594,
|
| 790 |
+
"learning_rate": 6.127906976744186e-05,
|
| 791 |
+
"loss": 13.3773,
|
| 792 |
+
"step": 5000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 49.0,
|
| 796 |
+
"eval_dummy": 1.0,
|
| 797 |
+
"eval_loss": 30.39496421813965,
|
| 798 |
+
"eval_runtime": 16.6402,
|
| 799 |
+
"eval_samples_per_second": 2.885,
|
| 800 |
+
"eval_steps_per_second": 0.601,
|
| 801 |
+
"step": 5096
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 49.03846153846154,
|
| 805 |
+
"grad_norm": 28.625978469848633,
|
| 806 |
+
"learning_rate": 6.0504651162790696e-05,
|
| 807 |
+
"loss": 12.9449,
|
| 808 |
+
"step": 5100
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 50.0,
|
| 812 |
+
"grad_norm": 30.444610595703125,
|
| 813 |
+
"learning_rate": 5.9730232558139533e-05,
|
| 814 |
+
"loss": 12.9506,
|
| 815 |
+
"step": 5200
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 50.0,
|
| 819 |
+
"eval_dummy": 1.0,
|
| 820 |
+
"eval_loss": 31.28708839416504,
|
| 821 |
+
"eval_runtime": 16.7982,
|
| 822 |
+
"eval_samples_per_second": 2.857,
|
| 823 |
+
"eval_steps_per_second": 0.595,
|
| 824 |
+
"step": 5200
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 50.96153846153846,
|
| 828 |
+
"grad_norm": 22.916648864746094,
|
| 829 |
+
"learning_rate": 5.895581395348837e-05,
|
| 830 |
+
"loss": 13.0674,
|
| 831 |
+
"step": 5300
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 51.0,
|
| 835 |
+
"eval_dummy": 1.0,
|
| 836 |
+
"eval_loss": 29.57108497619629,
|
| 837 |
+
"eval_runtime": 16.4065,
|
| 838 |
+
"eval_samples_per_second": 2.926,
|
| 839 |
+
"eval_steps_per_second": 0.61,
|
| 840 |
+
"step": 5304
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 51.92307692307692,
|
| 844 |
+
"grad_norm": 21.012855529785156,
|
| 845 |
+
"learning_rate": 5.818139534883721e-05,
|
| 846 |
+
"loss": 13.1265,
|
| 847 |
+
"step": 5400
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 52.0,
|
| 851 |
+
"eval_dummy": 1.0,
|
| 852 |
+
"eval_loss": 31.08868980407715,
|
| 853 |
+
"eval_runtime": 16.8841,
|
| 854 |
+
"eval_samples_per_second": 2.843,
|
| 855 |
+
"eval_steps_per_second": 0.592,
|
| 856 |
+
"step": 5408
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 52.88461538461539,
|
| 860 |
+
"grad_norm": 16.615829467773438,
|
| 861 |
+
"learning_rate": 5.740697674418606e-05,
|
| 862 |
+
"loss": 13.1392,
|
| 863 |
+
"step": 5500
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 53.0,
|
| 867 |
+
"eval_dummy": 1.0,
|
| 868 |
+
"eval_loss": 29.843284606933594,
|
| 869 |
+
"eval_runtime": 17.0042,
|
| 870 |
+
"eval_samples_per_second": 2.823,
|
| 871 |
+
"eval_steps_per_second": 0.588,
|
| 872 |
+
"step": 5512
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 53.84615384615385,
|
| 876 |
+
"grad_norm": 17.38899040222168,
|
| 877 |
+
"learning_rate": 5.6632558139534884e-05,
|
| 878 |
+
"loss": 12.6108,
|
| 879 |
+
"step": 5600
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 54.0,
|
| 883 |
+
"eval_dummy": 1.0,
|
| 884 |
+
"eval_loss": 29.643640518188477,
|
| 885 |
+
"eval_runtime": 16.9549,
|
| 886 |
+
"eval_samples_per_second": 2.831,
|
| 887 |
+
"eval_steps_per_second": 0.59,
|
| 888 |
+
"step": 5616
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 54.80769230769231,
|
| 892 |
+
"grad_norm": 20.021800994873047,
|
| 893 |
+
"learning_rate": 5.585813953488372e-05,
|
| 894 |
+
"loss": 12.7608,
|
| 895 |
+
"step": 5700
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 55.0,
|
| 899 |
+
"eval_dummy": 1.0,
|
| 900 |
+
"eval_loss": 29.870615005493164,
|
| 901 |
+
"eval_runtime": 16.4959,
|
| 902 |
+
"eval_samples_per_second": 2.91,
|
| 903 |
+
"eval_steps_per_second": 0.606,
|
| 904 |
+
"step": 5720
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 55.76923076923077,
|
| 908 |
+
"grad_norm": 19.976686477661133,
|
| 909 |
+
"learning_rate": 5.5083720930232566e-05,
|
| 910 |
+
"loss": 12.8723,
|
| 911 |
+
"step": 5800
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 56.0,
|
| 915 |
+
"eval_dummy": 1.0,
|
| 916 |
+
"eval_loss": 30.059600830078125,
|
| 917 |
+
"eval_runtime": 16.9691,
|
| 918 |
+
"eval_samples_per_second": 2.829,
|
| 919 |
+
"eval_steps_per_second": 0.589,
|
| 920 |
+
"step": 5824
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 56.73076923076923,
|
| 924 |
+
"grad_norm": 34.17774963378906,
|
| 925 |
+
"learning_rate": 5.4309302325581404e-05,
|
| 926 |
+
"loss": 12.5437,
|
| 927 |
+
"step": 5900
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 57.0,
|
| 931 |
+
"eval_dummy": 1.0,
|
| 932 |
+
"eval_loss": 30.136695861816406,
|
| 933 |
+
"eval_runtime": 16.1925,
|
| 934 |
+
"eval_samples_per_second": 2.964,
|
| 935 |
+
"eval_steps_per_second": 0.618,
|
| 936 |
+
"step": 5928
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 57.69230769230769,
|
| 940 |
+
"grad_norm": 16.256919860839844,
|
| 941 |
+
"learning_rate": 5.353488372093024e-05,
|
| 942 |
+
"loss": 12.1387,
|
| 943 |
+
"step": 6000
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 58.0,
|
| 947 |
+
"eval_dummy": 1.0,
|
| 948 |
+
"eval_loss": 30.4089298248291,
|
| 949 |
+
"eval_runtime": 17.0149,
|
| 950 |
+
"eval_samples_per_second": 2.821,
|
| 951 |
+
"eval_steps_per_second": 0.588,
|
| 952 |
+
"step": 6032
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 58.65384615384615,
|
| 956 |
+
"grad_norm": 24.035823822021484,
|
| 957 |
+
"learning_rate": 5.276046511627908e-05,
|
| 958 |
+
"loss": 12.948,
|
| 959 |
+
"step": 6100
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 59.0,
|
| 963 |
+
"eval_dummy": 1.0,
|
| 964 |
+
"eval_loss": 30.537500381469727,
|
| 965 |
+
"eval_runtime": 16.6335,
|
| 966 |
+
"eval_samples_per_second": 2.886,
|
| 967 |
+
"eval_steps_per_second": 0.601,
|
| 968 |
+
"step": 6136
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 59.61538461538461,
|
| 972 |
+
"grad_norm": 18.700029373168945,
|
| 973 |
+
"learning_rate": 5.1986046511627916e-05,
|
| 974 |
+
"loss": 12.2869,
|
| 975 |
+
"step": 6200
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 60.0,
|
| 979 |
+
"eval_dummy": 1.0,
|
| 980 |
+
"eval_loss": 32.38269805908203,
|
| 981 |
+
"eval_runtime": 16.6776,
|
| 982 |
+
"eval_samples_per_second": 2.878,
|
| 983 |
+
"eval_steps_per_second": 0.6,
|
| 984 |
+
"step": 6240
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 60.57692307692308,
|
| 988 |
+
"grad_norm": 34.31249237060547,
|
| 989 |
+
"learning_rate": 5.121162790697675e-05,
|
| 990 |
+
"loss": 12.7717,
|
| 991 |
+
"step": 6300
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 61.0,
|
| 995 |
+
"eval_dummy": 1.0,
|
| 996 |
+
"eval_loss": 30.639678955078125,
|
| 997 |
+
"eval_runtime": 16.6901,
|
| 998 |
+
"eval_samples_per_second": 2.876,
|
| 999 |
+
"eval_steps_per_second": 0.599,
|
| 1000 |
+
"step": 6344
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 61.53846153846154,
|
| 1004 |
+
"grad_norm": 26.939144134521484,
|
| 1005 |
+
"learning_rate": 5.0437209302325585e-05,
|
| 1006 |
+
"loss": 12.4924,
|
| 1007 |
+
"step": 6400
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 62.0,
|
| 1011 |
+
"eval_dummy": 1.0,
|
| 1012 |
+
"eval_loss": 30.700525283813477,
|
| 1013 |
+
"eval_runtime": 16.6341,
|
| 1014 |
+
"eval_samples_per_second": 2.886,
|
| 1015 |
+
"eval_steps_per_second": 0.601,
|
| 1016 |
+
"step": 6448
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 62.5,
|
| 1020 |
+
"grad_norm": 13.92809009552002,
|
| 1021 |
+
"learning_rate": 4.966279069767442e-05,
|
| 1022 |
+
"loss": 12.3031,
|
| 1023 |
+
"step": 6500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 63.0,
|
| 1027 |
+
"eval_dummy": 1.0,
|
| 1028 |
+
"eval_loss": 29.986501693725586,
|
| 1029 |
+
"eval_runtime": 16.2627,
|
| 1030 |
+
"eval_samples_per_second": 2.952,
|
| 1031 |
+
"eval_steps_per_second": 0.615,
|
| 1032 |
+
"step": 6552
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 63.46153846153846,
|
| 1036 |
+
"grad_norm": 53.49395751953125,
|
| 1037 |
+
"learning_rate": 4.888837209302326e-05,
|
| 1038 |
+
"loss": 12.5575,
|
| 1039 |
+
"step": 6600
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 64.0,
|
| 1043 |
+
"eval_dummy": 1.0,
|
| 1044 |
+
"eval_loss": 31.06968116760254,
|
| 1045 |
+
"eval_runtime": 16.634,
|
| 1046 |
+
"eval_samples_per_second": 2.886,
|
| 1047 |
+
"eval_steps_per_second": 0.601,
|
| 1048 |
+
"step": 6656
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 64.42307692307692,
|
| 1052 |
+
"grad_norm": 20.313173294067383,
|
| 1053 |
+
"learning_rate": 4.811395348837209e-05,
|
| 1054 |
+
"loss": 11.9496,
|
| 1055 |
+
"step": 6700
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 65.0,
|
| 1059 |
+
"eval_dummy": 1.0,
|
| 1060 |
+
"eval_loss": 31.579355239868164,
|
| 1061 |
+
"eval_runtime": 16.5822,
|
| 1062 |
+
"eval_samples_per_second": 2.895,
|
| 1063 |
+
"eval_steps_per_second": 0.603,
|
| 1064 |
+
"step": 6760
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 65.38461538461539,
|
| 1068 |
+
"grad_norm": 33.59545135498047,
|
| 1069 |
+
"learning_rate": 4.733953488372093e-05,
|
| 1070 |
+
"loss": 12.0462,
|
| 1071 |
+
"step": 6800
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 66.0,
|
| 1075 |
+
"eval_dummy": 1.0,
|
| 1076 |
+
"eval_loss": 31.65366554260254,
|
| 1077 |
+
"eval_runtime": 16.6216,
|
| 1078 |
+
"eval_samples_per_second": 2.888,
|
| 1079 |
+
"eval_steps_per_second": 0.602,
|
| 1080 |
+
"step": 6864
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 66.34615384615384,
|
| 1084 |
+
"grad_norm": 41.989036560058594,
|
| 1085 |
+
"learning_rate": 4.656511627906977e-05,
|
| 1086 |
+
"loss": 12.7167,
|
| 1087 |
+
"step": 6900
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 67.0,
|
| 1091 |
+
"eval_dummy": 1.0,
|
| 1092 |
+
"eval_loss": 30.74114990234375,
|
| 1093 |
+
"eval_runtime": 16.9556,
|
| 1094 |
+
"eval_samples_per_second": 2.831,
|
| 1095 |
+
"eval_steps_per_second": 0.59,
|
| 1096 |
+
"step": 6968
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 67.3076923076923,
|
| 1100 |
+
"grad_norm": 39.545814514160156,
|
| 1101 |
+
"learning_rate": 4.579069767441861e-05,
|
| 1102 |
+
"loss": 11.8595,
|
| 1103 |
+
"step": 7000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 68.0,
|
| 1107 |
+
"eval_dummy": 1.0,
|
| 1108 |
+
"eval_loss": 30.4969539642334,
|
| 1109 |
+
"eval_runtime": 16.5848,
|
| 1110 |
+
"eval_samples_per_second": 2.894,
|
| 1111 |
+
"eval_steps_per_second": 0.603,
|
| 1112 |
+
"step": 7072
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 68.26923076923077,
|
| 1116 |
+
"grad_norm": 17.500286102294922,
|
| 1117 |
+
"learning_rate": 4.501627906976745e-05,
|
| 1118 |
+
"loss": 11.7458,
|
| 1119 |
+
"step": 7100
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 69.0,
|
| 1123 |
+
"eval_dummy": 1.0,
|
| 1124 |
+
"eval_loss": 30.833221435546875,
|
| 1125 |
+
"eval_runtime": 16.7855,
|
| 1126 |
+
"eval_samples_per_second": 2.86,
|
| 1127 |
+
"eval_steps_per_second": 0.596,
|
| 1128 |
+
"step": 7176
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 69.23076923076923,
|
| 1132 |
+
"grad_norm": 18.128597259521484,
|
| 1133 |
+
"learning_rate": 4.4241860465116286e-05,
|
| 1134 |
+
"loss": 12.2058,
|
| 1135 |
+
"step": 7200
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 70.0,
|
| 1139 |
+
"eval_dummy": 1.0,
|
| 1140 |
+
"eval_loss": 32.0950813293457,
|
| 1141 |
+
"eval_runtime": 17.2742,
|
| 1142 |
+
"eval_samples_per_second": 2.779,
|
| 1143 |
+
"eval_steps_per_second": 0.579,
|
| 1144 |
+
"step": 7280
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 70.1923076923077,
|
| 1148 |
+
"grad_norm": 25.363075256347656,
|
| 1149 |
+
"learning_rate": 4.3467441860465117e-05,
|
| 1150 |
+
"loss": 12.0874,
|
| 1151 |
+
"step": 7300
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 71.0,
|
| 1155 |
+
"eval_dummy": 1.0,
|
| 1156 |
+
"eval_loss": 32.46952438354492,
|
| 1157 |
+
"eval_runtime": 17.4937,
|
| 1158 |
+
"eval_samples_per_second": 2.744,
|
| 1159 |
+
"eval_steps_per_second": 0.572,
|
| 1160 |
+
"step": 7384
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 71.15384615384616,
|
| 1164 |
+
"grad_norm": 9.088305473327637,
|
| 1165 |
+
"learning_rate": 4.2693023255813954e-05,
|
| 1166 |
+
"loss": 11.705,
|
| 1167 |
+
"step": 7400
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 72.0,
|
| 1171 |
+
"eval_dummy": 1.0,
|
| 1172 |
+
"eval_loss": 31.311721801757812,
|
| 1173 |
+
"eval_runtime": 16.6157,
|
| 1174 |
+
"eval_samples_per_second": 2.889,
|
| 1175 |
+
"eval_steps_per_second": 0.602,
|
| 1176 |
+
"step": 7488
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 72.11538461538461,
|
| 1180 |
+
"grad_norm": 21.332366943359375,
|
| 1181 |
+
"learning_rate": 4.191860465116279e-05,
|
| 1182 |
+
"loss": 12.0,
|
| 1183 |
+
"step": 7500
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 73.0,
|
| 1187 |
+
"eval_dummy": 1.0,
|
| 1188 |
+
"eval_loss": 30.654035568237305,
|
| 1189 |
+
"eval_runtime": 17.001,
|
| 1190 |
+
"eval_samples_per_second": 2.823,
|
| 1191 |
+
"eval_steps_per_second": 0.588,
|
| 1192 |
+
"step": 7592
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 73.07692307692308,
|
| 1196 |
+
"grad_norm": 16.92377281188965,
|
| 1197 |
+
"learning_rate": 4.114418604651163e-05,
|
| 1198 |
+
"loss": 11.9852,
|
| 1199 |
+
"step": 7600
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 74.0,
|
| 1203 |
+
"eval_dummy": 1.0,
|
| 1204 |
+
"eval_loss": 34.29496765136719,
|
| 1205 |
+
"eval_runtime": 16.6247,
|
| 1206 |
+
"eval_samples_per_second": 2.887,
|
| 1207 |
+
"eval_steps_per_second": 0.602,
|
| 1208 |
+
"step": 7696
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 74.03846153846153,
|
| 1212 |
+
"grad_norm": 47.94444274902344,
|
| 1213 |
+
"learning_rate": 4.0369767441860474e-05,
|
| 1214 |
+
"loss": 11.8647,
|
| 1215 |
+
"step": 7700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 75.0,
|
| 1219 |
+
"grad_norm": 31.79910659790039,
|
| 1220 |
+
"learning_rate": 3.959534883720931e-05,
|
| 1221 |
+
"loss": 11.7597,
|
| 1222 |
+
"step": 7800
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 75.0,
|
| 1226 |
+
"eval_dummy": 1.0,
|
| 1227 |
+
"eval_loss": 31.636077880859375,
|
| 1228 |
+
"eval_runtime": 16.64,
|
| 1229 |
+
"eval_samples_per_second": 2.885,
|
| 1230 |
+
"eval_steps_per_second": 0.601,
|
| 1231 |
+
"step": 7800
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 75.96153846153847,
|
| 1235 |
+
"grad_norm": 17.918701171875,
|
| 1236 |
+
"learning_rate": 3.882093023255814e-05,
|
| 1237 |
+
"loss": 11.8713,
|
| 1238 |
+
"step": 7900
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 76.0,
|
| 1242 |
+
"eval_dummy": 1.0,
|
| 1243 |
+
"eval_loss": 31.10820198059082,
|
| 1244 |
+
"eval_runtime": 16.6206,
|
| 1245 |
+
"eval_samples_per_second": 2.888,
|
| 1246 |
+
"eval_steps_per_second": 0.602,
|
| 1247 |
+
"step": 7904
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 76.92307692307692,
|
| 1251 |
+
"grad_norm": 34.80290985107422,
|
| 1252 |
+
"learning_rate": 3.804651162790698e-05,
|
| 1253 |
+
"loss": 11.705,
|
| 1254 |
+
"step": 8000
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 77.0,
|
| 1258 |
+
"eval_dummy": 1.0,
|
| 1259 |
+
"eval_loss": 31.87137794494629,
|
| 1260 |
+
"eval_runtime": 16.986,
|
| 1261 |
+
"eval_samples_per_second": 2.826,
|
| 1262 |
+
"eval_steps_per_second": 0.589,
|
| 1263 |
+
"step": 8008
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 77.88461538461539,
|
| 1267 |
+
"grad_norm": 16.33148193359375,
|
| 1268 |
+
"learning_rate": 3.727209302325582e-05,
|
| 1269 |
+
"loss": 11.5474,
|
| 1270 |
+
"step": 8100
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 78.0,
|
| 1274 |
+
"eval_dummy": 1.0,
|
| 1275 |
+
"eval_loss": 31.029922485351562,
|
| 1276 |
+
"eval_runtime": 16.598,
|
| 1277 |
+
"eval_samples_per_second": 2.892,
|
| 1278 |
+
"eval_steps_per_second": 0.602,
|
| 1279 |
+
"step": 8112
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 78.84615384615384,
|
| 1283 |
+
"grad_norm": 15.126340866088867,
|
| 1284 |
+
"learning_rate": 3.6497674418604655e-05,
|
| 1285 |
+
"loss": 11.8387,
|
| 1286 |
+
"step": 8200
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 79.0,
|
| 1290 |
+
"eval_dummy": 1.0,
|
| 1291 |
+
"eval_loss": 31.367172241210938,
|
| 1292 |
+
"eval_runtime": 16.6089,
|
| 1293 |
+
"eval_samples_per_second": 2.89,
|
| 1294 |
+
"eval_steps_per_second": 0.602,
|
| 1295 |
+
"step": 8216
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 79.8076923076923,
|
| 1299 |
+
"grad_norm": 13.069074630737305,
|
| 1300 |
+
"learning_rate": 3.5723255813953486e-05,
|
| 1301 |
+
"loss": 11.7057,
|
| 1302 |
+
"step": 8300
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 80.0,
|
| 1306 |
+
"eval_dummy": 1.0,
|
| 1307 |
+
"eval_loss": 31.643484115600586,
|
| 1308 |
+
"eval_runtime": 16.4881,
|
| 1309 |
+
"eval_samples_per_second": 2.911,
|
| 1310 |
+
"eval_steps_per_second": 0.606,
|
| 1311 |
+
"step": 8320
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 80.76923076923077,
|
| 1315 |
+
"grad_norm": 24.73469352722168,
|
| 1316 |
+
"learning_rate": 3.4948837209302323e-05,
|
| 1317 |
+
"loss": 11.5656,
|
| 1318 |
+
"step": 8400
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 81.0,
|
| 1322 |
+
"eval_dummy": 1.0,
|
| 1323 |
+
"eval_loss": 31.194046020507812,
|
| 1324 |
+
"eval_runtime": 16.6985,
|
| 1325 |
+
"eval_samples_per_second": 2.875,
|
| 1326 |
+
"eval_steps_per_second": 0.599,
|
| 1327 |
+
"step": 8424
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 81.73076923076923,
|
| 1331 |
+
"grad_norm": 26.05837631225586,
|
| 1332 |
+
"learning_rate": 3.417441860465117e-05,
|
| 1333 |
+
"loss": 11.6578,
|
| 1334 |
+
"step": 8500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 82.0,
|
| 1338 |
+
"eval_dummy": 1.0,
|
| 1339 |
+
"eval_loss": 31.818357467651367,
|
| 1340 |
+
"eval_runtime": 16.6321,
|
| 1341 |
+
"eval_samples_per_second": 2.886,
|
| 1342 |
+
"eval_steps_per_second": 0.601,
|
| 1343 |
+
"step": 8528
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 82.6923076923077,
|
| 1347 |
+
"grad_norm": 29.041229248046875,
|
| 1348 |
+
"learning_rate": 3.3400000000000005e-05,
|
| 1349 |
+
"loss": 11.3049,
|
| 1350 |
+
"step": 8600
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 83.0,
|
| 1354 |
+
"eval_dummy": 1.0,
|
| 1355 |
+
"eval_loss": 31.866790771484375,
|
| 1356 |
+
"eval_runtime": 16.6756,
|
| 1357 |
+
"eval_samples_per_second": 2.878,
|
| 1358 |
+
"eval_steps_per_second": 0.6,
|
| 1359 |
+
"step": 8632
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 83.65384615384616,
|
| 1363 |
+
"grad_norm": 14.160347938537598,
|
| 1364 |
+
"learning_rate": 3.262558139534884e-05,
|
| 1365 |
+
"loss": 11.5542,
|
| 1366 |
+
"step": 8700
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 84.0,
|
| 1370 |
+
"eval_dummy": 1.0,
|
| 1371 |
+
"eval_loss": 32.81920623779297,
|
| 1372 |
+
"eval_runtime": 16.6408,
|
| 1373 |
+
"eval_samples_per_second": 2.884,
|
| 1374 |
+
"eval_steps_per_second": 0.601,
|
| 1375 |
+
"step": 8736
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 84.61538461538461,
|
| 1379 |
+
"grad_norm": 11.912644386291504,
|
| 1380 |
+
"learning_rate": 3.185116279069768e-05,
|
| 1381 |
+
"loss": 11.3942,
|
| 1382 |
+
"step": 8800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 85.0,
|
| 1386 |
+
"eval_dummy": 1.0,
|
| 1387 |
+
"eval_loss": 30.972320556640625,
|
| 1388 |
+
"eval_runtime": 16.7795,
|
| 1389 |
+
"eval_samples_per_second": 2.861,
|
| 1390 |
+
"eval_steps_per_second": 0.596,
|
| 1391 |
+
"step": 8840
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 85.57692307692308,
|
| 1395 |
+
"grad_norm": 19.492916107177734,
|
| 1396 |
+
"learning_rate": 3.107674418604651e-05,
|
| 1397 |
+
"loss": 11.6955,
|
| 1398 |
+
"step": 8900
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 86.0,
|
| 1402 |
+
"eval_dummy": 1.0,
|
| 1403 |
+
"eval_loss": 31.348657608032227,
|
| 1404 |
+
"eval_runtime": 16.743,
|
| 1405 |
+
"eval_samples_per_second": 2.867,
|
| 1406 |
+
"eval_steps_per_second": 0.597,
|
| 1407 |
+
"step": 8944
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 86.53846153846153,
|
| 1411 |
+
"grad_norm": 14.419718742370605,
|
| 1412 |
+
"learning_rate": 3.0302325581395346e-05,
|
| 1413 |
+
"loss": 11.4862,
|
| 1414 |
+
"step": 9000
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 87.0,
|
| 1418 |
+
"eval_dummy": 1.0,
|
| 1419 |
+
"eval_loss": 32.045135498046875,
|
| 1420 |
+
"eval_runtime": 16.7069,
|
| 1421 |
+
"eval_samples_per_second": 2.873,
|
| 1422 |
+
"eval_steps_per_second": 0.599,
|
| 1423 |
+
"step": 9048
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 87.5,
|
| 1427 |
+
"grad_norm": 24.9334659576416,
|
| 1428 |
+
"learning_rate": 2.9527906976744187e-05,
|
| 1429 |
+
"loss": 11.5867,
|
| 1430 |
+
"step": 9100
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 88.0,
|
| 1434 |
+
"eval_dummy": 1.0,
|
| 1435 |
+
"eval_loss": 31.976896286010742,
|
| 1436 |
+
"eval_runtime": 16.5865,
|
| 1437 |
+
"eval_samples_per_second": 2.894,
|
| 1438 |
+
"eval_steps_per_second": 0.603,
|
| 1439 |
+
"step": 9152
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 88.46153846153847,
|
| 1443 |
+
"grad_norm": 10.158917427062988,
|
| 1444 |
+
"learning_rate": 2.8753488372093018e-05,
|
| 1445 |
+
"loss": 11.0975,
|
| 1446 |
+
"step": 9200
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 89.0,
|
| 1450 |
+
"eval_dummy": 1.0,
|
| 1451 |
+
"eval_loss": 31.972078323364258,
|
| 1452 |
+
"eval_runtime": 16.6959,
|
| 1453 |
+
"eval_samples_per_second": 2.875,
|
| 1454 |
+
"eval_steps_per_second": 0.599,
|
| 1455 |
+
"step": 9256
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 89.42307692307692,
|
| 1459 |
+
"grad_norm": 11.408435821533203,
|
| 1460 |
+
"learning_rate": 2.797906976744187e-05,
|
| 1461 |
+
"loss": 11.5126,
|
| 1462 |
+
"step": 9300
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 90.0,
|
| 1466 |
+
"eval_dummy": 1.0,
|
| 1467 |
+
"eval_loss": 35.387664794921875,
|
| 1468 |
+
"eval_runtime": 16.6889,
|
| 1469 |
+
"eval_samples_per_second": 2.876,
|
| 1470 |
+
"eval_steps_per_second": 0.599,
|
| 1471 |
+
"step": 9360
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 90.38461538461539,
|
| 1475 |
+
"grad_norm": 18.4831600189209,
|
| 1476 |
+
"learning_rate": 2.72046511627907e-05,
|
| 1477 |
+
"loss": 11.067,
|
| 1478 |
+
"step": 9400
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 91.0,
|
| 1482 |
+
"eval_dummy": 1.0,
|
| 1483 |
+
"eval_loss": 33.76138687133789,
|
| 1484 |
+
"eval_runtime": 16.2325,
|
| 1485 |
+
"eval_samples_per_second": 2.957,
|
| 1486 |
+
"eval_steps_per_second": 0.616,
|
| 1487 |
+
"step": 9464
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 91.34615384615384,
|
| 1491 |
+
"grad_norm": 14.10232925415039,
|
| 1492 |
+
"learning_rate": 2.643023255813954e-05,
|
| 1493 |
+
"loss": 11.3857,
|
| 1494 |
+
"step": 9500
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 92.0,
|
| 1498 |
+
"eval_dummy": 1.0,
|
| 1499 |
+
"eval_loss": 32.704566955566406,
|
| 1500 |
+
"eval_runtime": 16.6368,
|
| 1501 |
+
"eval_samples_per_second": 2.885,
|
| 1502 |
+
"eval_steps_per_second": 0.601,
|
| 1503 |
+
"step": 9568
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 92.3076923076923,
|
| 1507 |
+
"grad_norm": 10.36620807647705,
|
| 1508 |
+
"learning_rate": 2.565581395348837e-05,
|
| 1509 |
+
"loss": 11.5511,
|
| 1510 |
+
"step": 9600
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 93.0,
|
| 1514 |
+
"eval_dummy": 1.0,
|
| 1515 |
+
"eval_loss": 32.10957336425781,
|
| 1516 |
+
"eval_runtime": 16.8564,
|
| 1517 |
+
"eval_samples_per_second": 2.848,
|
| 1518 |
+
"eval_steps_per_second": 0.593,
|
| 1519 |
+
"step": 9672
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 93.26923076923077,
|
| 1523 |
+
"grad_norm": 13.063793182373047,
|
| 1524 |
+
"learning_rate": 2.488139534883721e-05,
|
| 1525 |
+
"loss": 11.0961,
|
| 1526 |
+
"step": 9700
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 94.0,
|
| 1530 |
+
"eval_dummy": 1.0,
|
| 1531 |
+
"eval_loss": 32.8302001953125,
|
| 1532 |
+
"eval_runtime": 16.6194,
|
| 1533 |
+
"eval_samples_per_second": 2.888,
|
| 1534 |
+
"eval_steps_per_second": 0.602,
|
| 1535 |
+
"step": 9776
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 94.23076923076923,
|
| 1539 |
+
"grad_norm": 47.0684814453125,
|
| 1540 |
+
"learning_rate": 2.4106976744186043e-05,
|
| 1541 |
+
"loss": 11.2935,
|
| 1542 |
+
"step": 9800
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 95.0,
|
| 1546 |
+
"eval_dummy": 1.0,
|
| 1547 |
+
"eval_loss": 32.66879653930664,
|
| 1548 |
+
"eval_runtime": 16.8788,
|
| 1549 |
+
"eval_samples_per_second": 2.844,
|
| 1550 |
+
"eval_steps_per_second": 0.592,
|
| 1551 |
+
"step": 9880
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 95.1923076923077,
|
| 1555 |
+
"grad_norm": 16.18996238708496,
|
| 1556 |
+
"learning_rate": 2.333255813953488e-05,
|
| 1557 |
+
"loss": 11.2398,
|
| 1558 |
+
"step": 9900
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 96.0,
|
| 1562 |
+
"eval_dummy": 1.0,
|
| 1563 |
+
"eval_loss": 32.2806510925293,
|
| 1564 |
+
"eval_runtime": 16.4167,
|
| 1565 |
+
"eval_samples_per_second": 2.924,
|
| 1566 |
+
"eval_steps_per_second": 0.609,
|
| 1567 |
+
"step": 9984
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 96.15384615384616,
|
| 1571 |
+
"grad_norm": 20.301530838012695,
|
| 1572 |
+
"learning_rate": 2.2558139534883715e-05,
|
| 1573 |
+
"loss": 11.0444,
|
| 1574 |
+
"step": 10000
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 97.0,
|
| 1578 |
+
"eval_dummy": 1.0,
|
| 1579 |
+
"eval_loss": 32.276641845703125,
|
| 1580 |
+
"eval_runtime": 16.7261,
|
| 1581 |
+
"eval_samples_per_second": 2.87,
|
| 1582 |
+
"eval_steps_per_second": 0.598,
|
| 1583 |
+
"step": 10088
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 97.11538461538461,
|
| 1587 |
+
"grad_norm": 16.50993537902832,
|
| 1588 |
+
"learning_rate": 2.1783720930232563e-05,
|
| 1589 |
+
"loss": 11.3157,
|
| 1590 |
+
"step": 10100
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 98.0,
|
| 1594 |
+
"eval_dummy": 1.0,
|
| 1595 |
+
"eval_loss": 32.443729400634766,
|
| 1596 |
+
"eval_runtime": 16.7525,
|
| 1597 |
+
"eval_samples_per_second": 2.865,
|
| 1598 |
+
"eval_steps_per_second": 0.597,
|
| 1599 |
+
"step": 10192
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 98.07692307692308,
|
| 1603 |
+
"grad_norm": 13.487881660461426,
|
| 1604 |
+
"learning_rate": 2.1009302325581397e-05,
|
| 1605 |
+
"loss": 11.0191,
|
| 1606 |
+
"step": 10200
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 99.0,
|
| 1610 |
+
"eval_dummy": 1.0,
|
| 1611 |
+
"eval_loss": 32.385108947753906,
|
| 1612 |
+
"eval_runtime": 16.6154,
|
| 1613 |
+
"eval_samples_per_second": 2.889,
|
| 1614 |
+
"eval_steps_per_second": 0.602,
|
| 1615 |
+
"step": 10296
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 99.03846153846153,
|
| 1619 |
+
"grad_norm": 13.905572891235352,
|
| 1620 |
+
"learning_rate": 2.0234883720930235e-05,
|
| 1621 |
+
"loss": 11.2286,
|
| 1622 |
+
"step": 10300
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 100.0,
|
| 1626 |
+
"grad_norm": 37.709373474121094,
|
| 1627 |
+
"learning_rate": 1.946046511627907e-05,
|
| 1628 |
+
"loss": 11.1406,
|
| 1629 |
+
"step": 10400
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 100.0,
|
| 1633 |
+
"eval_dummy": 1.0,
|
| 1634 |
+
"eval_loss": 32.138919830322266,
|
| 1635 |
+
"eval_runtime": 16.6356,
|
| 1636 |
+
"eval_samples_per_second": 2.885,
|
| 1637 |
+
"eval_steps_per_second": 0.601,
|
| 1638 |
+
"step": 10400
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 100.96153846153847,
|
| 1642 |
+
"grad_norm": 9.66380500793457,
|
| 1643 |
+
"learning_rate": 1.8686046511627907e-05,
|
| 1644 |
+
"loss": 11.1237,
|
| 1645 |
+
"step": 10500
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 101.0,
|
| 1649 |
+
"eval_dummy": 1.0,
|
| 1650 |
+
"eval_loss": 32.488643646240234,
|
| 1651 |
+
"eval_runtime": 16.5945,
|
| 1652 |
+
"eval_samples_per_second": 2.893,
|
| 1653 |
+
"eval_steps_per_second": 0.603,
|
| 1654 |
+
"step": 10504
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 101.92307692307692,
|
| 1658 |
+
"grad_norm": 8.697158813476562,
|
| 1659 |
+
"learning_rate": 1.791162790697674e-05,
|
| 1660 |
+
"loss": 10.9485,
|
| 1661 |
+
"step": 10600
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 102.0,
|
| 1665 |
+
"eval_dummy": 1.0,
|
| 1666 |
+
"eval_loss": 32.50514602661133,
|
| 1667 |
+
"eval_runtime": 16.4431,
|
| 1668 |
+
"eval_samples_per_second": 2.919,
|
| 1669 |
+
"eval_steps_per_second": 0.608,
|
| 1670 |
+
"step": 10608
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 102.88461538461539,
|
| 1674 |
+
"grad_norm": 7.563882350921631,
|
| 1675 |
+
"learning_rate": 1.713720930232558e-05,
|
| 1676 |
+
"loss": 10.9188,
|
| 1677 |
+
"step": 10700
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 103.0,
|
| 1681 |
+
"eval_dummy": 1.0,
|
| 1682 |
+
"eval_loss": 32.86152648925781,
|
| 1683 |
+
"eval_runtime": 16.6025,
|
| 1684 |
+
"eval_samples_per_second": 2.891,
|
| 1685 |
+
"eval_steps_per_second": 0.602,
|
| 1686 |
+
"step": 10712
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 103.84615384615384,
|
| 1690 |
+
"grad_norm": 9.366110801696777,
|
| 1691 |
+
"learning_rate": 1.6362790697674413e-05,
|
| 1692 |
+
"loss": 11.3029,
|
| 1693 |
+
"step": 10800
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 104.0,
|
| 1697 |
+
"eval_dummy": 1.0,
|
| 1698 |
+
"eval_loss": 33.038761138916016,
|
| 1699 |
+
"eval_runtime": 16.8928,
|
| 1700 |
+
"eval_samples_per_second": 2.841,
|
| 1701 |
+
"eval_steps_per_second": 0.592,
|
| 1702 |
+
"step": 10816
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 104.8076923076923,
|
| 1706 |
+
"grad_norm": 28.598913192749023,
|
| 1707 |
+
"learning_rate": 1.558837209302326e-05,
|
| 1708 |
+
"loss": 11.2023,
|
| 1709 |
+
"step": 10900
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 105.0,
|
| 1713 |
+
"eval_dummy": 1.0,
|
| 1714 |
+
"eval_loss": 32.492279052734375,
|
| 1715 |
+
"eval_runtime": 16.6606,
|
| 1716 |
+
"eval_samples_per_second": 2.881,
|
| 1717 |
+
"eval_steps_per_second": 0.6,
|
| 1718 |
+
"step": 10920
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 105.76923076923077,
|
| 1722 |
+
"grad_norm": 23.246570587158203,
|
| 1723 |
+
"learning_rate": 1.4813953488372098e-05,
|
| 1724 |
+
"loss": 10.9634,
|
| 1725 |
+
"step": 11000
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 106.0,
|
| 1729 |
+
"eval_dummy": 1.0,
|
| 1730 |
+
"eval_loss": 32.32876968383789,
|
| 1731 |
+
"eval_runtime": 16.8242,
|
| 1732 |
+
"eval_samples_per_second": 2.853,
|
| 1733 |
+
"eval_steps_per_second": 0.594,
|
| 1734 |
+
"step": 11024
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 106.73076923076923,
|
| 1738 |
+
"grad_norm": 12.571370124816895,
|
| 1739 |
+
"learning_rate": 1.4039534883720934e-05,
|
| 1740 |
+
"loss": 11.257,
|
| 1741 |
+
"step": 11100
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 107.0,
|
| 1745 |
+
"eval_dummy": 1.0,
|
| 1746 |
+
"eval_loss": 31.88549041748047,
|
| 1747 |
+
"eval_runtime": 16.349,
|
| 1748 |
+
"eval_samples_per_second": 2.936,
|
| 1749 |
+
"eval_steps_per_second": 0.612,
|
| 1750 |
+
"step": 11128
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 107.6923076923077,
|
| 1754 |
+
"grad_norm": 26.309329986572266,
|
| 1755 |
+
"learning_rate": 1.326511627906977e-05,
|
| 1756 |
+
"loss": 11.0193,
|
| 1757 |
+
"step": 11200
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 108.0,
|
| 1761 |
+
"eval_dummy": 1.0,
|
| 1762 |
+
"eval_loss": 34.006710052490234,
|
| 1763 |
+
"eval_runtime": 17.4954,
|
| 1764 |
+
"eval_samples_per_second": 2.744,
|
| 1765 |
+
"eval_steps_per_second": 0.572,
|
| 1766 |
+
"step": 11232
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 108.65384615384616,
|
| 1770 |
+
"grad_norm": 21.006258010864258,
|
| 1771 |
+
"learning_rate": 1.2490697674418606e-05,
|
| 1772 |
+
"loss": 10.6401,
|
| 1773 |
+
"step": 11300
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 109.0,
|
| 1777 |
+
"eval_dummy": 1.0,
|
| 1778 |
+
"eval_loss": 33.29460144042969,
|
| 1779 |
+
"eval_runtime": 16.6851,
|
| 1780 |
+
"eval_samples_per_second": 2.877,
|
| 1781 |
+
"eval_steps_per_second": 0.599,
|
| 1782 |
+
"step": 11336
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 109.61538461538461,
|
| 1786 |
+
"grad_norm": 17.321447372436523,
|
| 1787 |
+
"learning_rate": 1.1716279069767442e-05,
|
| 1788 |
+
"loss": 11.0542,
|
| 1789 |
+
"step": 11400
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 110.0,
|
| 1793 |
+
"eval_dummy": 1.0,
|
| 1794 |
+
"eval_loss": 34.05351638793945,
|
| 1795 |
+
"eval_runtime": 16.6555,
|
| 1796 |
+
"eval_samples_per_second": 2.882,
|
| 1797 |
+
"eval_steps_per_second": 0.6,
|
| 1798 |
+
"step": 11440
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 110.57692307692308,
|
| 1802 |
+
"grad_norm": 15.087108612060547,
|
| 1803 |
+
"learning_rate": 1.0941860465116278e-05,
|
| 1804 |
+
"loss": 10.888,
|
| 1805 |
+
"step": 11500
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 111.0,
|
| 1809 |
+
"eval_dummy": 1.0,
|
| 1810 |
+
"eval_loss": 32.72056198120117,
|
| 1811 |
+
"eval_runtime": 16.9072,
|
| 1812 |
+
"eval_samples_per_second": 2.839,
|
| 1813 |
+
"eval_steps_per_second": 0.591,
|
| 1814 |
+
"step": 11544
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 111.53846153846153,
|
| 1818 |
+
"grad_norm": 8.586106300354004,
|
| 1819 |
+
"learning_rate": 1.0167441860465113e-05,
|
| 1820 |
+
"loss": 10.9706,
|
| 1821 |
+
"step": 11600
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 112.0,
|
| 1825 |
+
"eval_dummy": 1.0,
|
| 1826 |
+
"eval_loss": 33.12382888793945,
|
| 1827 |
+
"eval_runtime": 16.5804,
|
| 1828 |
+
"eval_samples_per_second": 2.895,
|
| 1829 |
+
"eval_steps_per_second": 0.603,
|
| 1830 |
+
"step": 11648
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 112.5,
|
| 1834 |
+
"grad_norm": 7.436498165130615,
|
| 1835 |
+
"learning_rate": 9.39302325581396e-06,
|
| 1836 |
+
"loss": 11.0075,
|
| 1837 |
+
"step": 11700
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 113.0,
|
| 1841 |
+
"eval_dummy": 1.0,
|
| 1842 |
+
"eval_loss": 32.988155364990234,
|
| 1843 |
+
"eval_runtime": 16.4227,
|
| 1844 |
+
"eval_samples_per_second": 2.923,
|
| 1845 |
+
"eval_steps_per_second": 0.609,
|
| 1846 |
+
"step": 11752
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 113.46153846153847,
|
| 1850 |
+
"grad_norm": 8.474443435668945,
|
| 1851 |
+
"learning_rate": 8.618604651162795e-06,
|
| 1852 |
+
"loss": 10.7895,
|
| 1853 |
+
"step": 11800
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 114.0,
|
| 1857 |
+
"eval_dummy": 1.0,
|
| 1858 |
+
"eval_loss": 32.79851150512695,
|
| 1859 |
+
"eval_runtime": 17.5126,
|
| 1860 |
+
"eval_samples_per_second": 2.741,
|
| 1861 |
+
"eval_steps_per_second": 0.571,
|
| 1862 |
+
"step": 11856
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 114.42307692307692,
|
| 1866 |
+
"grad_norm": 17.689861297607422,
|
| 1867 |
+
"learning_rate": 7.844186046511631e-06,
|
| 1868 |
+
"loss": 10.9181,
|
| 1869 |
+
"step": 11900
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 115.0,
|
| 1873 |
+
"eval_dummy": 1.0,
|
| 1874 |
+
"eval_loss": 32.91426086425781,
|
| 1875 |
+
"eval_runtime": 17.7135,
|
| 1876 |
+
"eval_samples_per_second": 2.71,
|
| 1877 |
+
"eval_steps_per_second": 0.565,
|
| 1878 |
+
"step": 11960
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 115.38461538461539,
|
| 1882 |
+
"grad_norm": 10.550300598144531,
|
| 1883 |
+
"learning_rate": 7.069767441860467e-06,
|
| 1884 |
+
"loss": 10.5938,
|
| 1885 |
+
"step": 12000
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 116.0,
|
| 1889 |
+
"eval_dummy": 1.0,
|
| 1890 |
+
"eval_loss": 33.07219314575195,
|
| 1891 |
+
"eval_runtime": 16.7996,
|
| 1892 |
+
"eval_samples_per_second": 2.857,
|
| 1893 |
+
"eval_steps_per_second": 0.595,
|
| 1894 |
+
"step": 12064
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 116.34615384615384,
|
| 1898 |
+
"grad_norm": 10.545084953308105,
|
| 1899 |
+
"learning_rate": 6.295348837209302e-06,
|
| 1900 |
+
"loss": 10.4932,
|
| 1901 |
+
"step": 12100
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 117.0,
|
| 1905 |
+
"eval_dummy": 1.0,
|
| 1906 |
+
"eval_loss": 34.2365837097168,
|
| 1907 |
+
"eval_runtime": 17.0204,
|
| 1908 |
+
"eval_samples_per_second": 2.82,
|
| 1909 |
+
"eval_steps_per_second": 0.588,
|
| 1910 |
+
"step": 12168
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 117.3076923076923,
|
| 1914 |
+
"grad_norm": 11.177499771118164,
|
| 1915 |
+
"learning_rate": 5.520930232558138e-06,
|
| 1916 |
+
"loss": 10.9761,
|
| 1917 |
+
"step": 12200
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 118.0,
|
| 1921 |
+
"eval_dummy": 1.0,
|
| 1922 |
+
"eval_loss": 33.88801956176758,
|
| 1923 |
+
"eval_runtime": 16.5143,
|
| 1924 |
+
"eval_samples_per_second": 2.907,
|
| 1925 |
+
"eval_steps_per_second": 0.606,
|
| 1926 |
+
"step": 12272
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 118.26923076923077,
|
| 1930 |
+
"grad_norm": 9.421356201171875,
|
| 1931 |
+
"learning_rate": 4.746511627906974e-06,
|
| 1932 |
+
"loss": 10.6918,
|
| 1933 |
+
"step": 12300
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 119.0,
|
| 1937 |
+
"eval_dummy": 1.0,
|
| 1938 |
+
"eval_loss": 34.32889175415039,
|
| 1939 |
+
"eval_runtime": 17.2621,
|
| 1940 |
+
"eval_samples_per_second": 2.781,
|
| 1941 |
+
"eval_steps_per_second": 0.579,
|
| 1942 |
+
"step": 12376
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 119.23076923076923,
|
| 1946 |
+
"grad_norm": 11.958416938781738,
|
| 1947 |
+
"learning_rate": 3.97209302325581e-06,
|
| 1948 |
+
"loss": 10.896,
|
| 1949 |
+
"step": 12400
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 120.0,
|
| 1953 |
+
"eval_dummy": 1.0,
|
| 1954 |
+
"eval_loss": 33.60952377319336,
|
| 1955 |
+
"eval_runtime": 17.2959,
|
| 1956 |
+
"eval_samples_per_second": 2.775,
|
| 1957 |
+
"eval_steps_per_second": 0.578,
|
| 1958 |
+
"step": 12480
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 120.1923076923077,
|
| 1962 |
+
"grad_norm": 7.985867023468018,
|
| 1963 |
+
"learning_rate": 3.1976744186046562e-06,
|
| 1964 |
+
"loss": 10.6876,
|
| 1965 |
+
"step": 12500
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 121.0,
|
| 1969 |
+
"eval_dummy": 1.0,
|
| 1970 |
+
"eval_loss": 33.86077880859375,
|
| 1971 |
+
"eval_runtime": 17.1725,
|
| 1972 |
+
"eval_samples_per_second": 2.795,
|
| 1973 |
+
"eval_steps_per_second": 0.582,
|
| 1974 |
+
"step": 12584
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 121.15384615384616,
|
| 1978 |
+
"grad_norm": 7.811230182647705,
|
| 1979 |
+
"learning_rate": 2.4232558139534926e-06,
|
| 1980 |
+
"loss": 10.5666,
|
| 1981 |
+
"step": 12600
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 122.0,
|
| 1985 |
+
"eval_dummy": 1.0,
|
| 1986 |
+
"eval_loss": 33.69937515258789,
|
| 1987 |
+
"eval_runtime": 16.6446,
|
| 1988 |
+
"eval_samples_per_second": 2.884,
|
| 1989 |
+
"eval_steps_per_second": 0.601,
|
| 1990 |
+
"step": 12688
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 122.11538461538461,
|
| 1994 |
+
"grad_norm": 6.883728504180908,
|
| 1995 |
+
"learning_rate": 1.6488372093023285e-06,
|
| 1996 |
+
"loss": 10.8161,
|
| 1997 |
+
"step": 12700
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 123.0,
|
| 2001 |
+
"eval_dummy": 1.0,
|
| 2002 |
+
"eval_loss": 33.61716842651367,
|
| 2003 |
+
"eval_runtime": 17.0639,
|
| 2004 |
+
"eval_samples_per_second": 2.813,
|
| 2005 |
+
"eval_steps_per_second": 0.586,
|
| 2006 |
+
"step": 12792
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 123.07692307692308,
|
| 2010 |
+
"grad_norm": 7.218296527862549,
|
| 2011 |
+
"learning_rate": 8.744186046511642e-07,
|
| 2012 |
+
"loss": 10.7195,
|
| 2013 |
+
"step": 12800
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 124.0,
|
| 2017 |
+
"eval_dummy": 1.0,
|
| 2018 |
+
"eval_loss": 33.539737701416016,
|
| 2019 |
+
"eval_runtime": 16.3513,
|
| 2020 |
+
"eval_samples_per_second": 2.936,
|
| 2021 |
+
"eval_steps_per_second": 0.612,
|
| 2022 |
+
"step": 12896
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 124.03846153846153,
|
| 2026 |
+
"grad_norm": 7.083764553070068,
|
| 2027 |
+
"learning_rate": 9.999999999999998e-08,
|
| 2028 |
+
"loss": 10.6712,
|
| 2029 |
+
"step": 12900
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 124.03846153846153,
|
| 2033 |
+
"eval_dummy": 1.0,
|
| 2034 |
+
"eval_loss": 33.490596771240234,
|
| 2035 |
+
"eval_runtime": 17.1907,
|
| 2036 |
+
"eval_samples_per_second": 2.792,
|
| 2037 |
+
"eval_steps_per_second": 0.582,
|
| 2038 |
+
"step": 12900
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 124.03846153846153,
|
| 2042 |
+
"step": 12900,
|
| 2043 |
+
"total_flos": 1.8148731642810335e+19,
|
| 2044 |
+
"train_loss": 14.019830729166667,
|
| 2045 |
+
"train_runtime": 31415.0856,
|
| 2046 |
+
"train_samples_per_second": 2.053,
|
| 2047 |
+
"train_steps_per_second": 0.411
|
| 2048 |
+
}
|
| 2049 |
+
],
|
| 2050 |
+
"logging_steps": 100,
|
| 2051 |
+
"max_steps": 12900,
|
| 2052 |
+
"num_input_tokens_seen": 0,
|
| 2053 |
+
"num_train_epochs": 125,
|
| 2054 |
+
"save_steps": 500,
|
| 2055 |
+
"stateful_callbacks": {
|
| 2056 |
+
"TrainerControl": {
|
| 2057 |
+
"args": {
|
| 2058 |
+
"should_epoch_stop": false,
|
| 2059 |
+
"should_evaluate": false,
|
| 2060 |
+
"should_log": false,
|
| 2061 |
+
"should_save": true,
|
| 2062 |
+
"should_training_stop": true
|
| 2063 |
+
},
|
| 2064 |
+
"attributes": {}
|
| 2065 |
+
}
|
| 2066 |
+
},
|
| 2067 |
+
"total_flos": 1.8148731642810335e+19,
|
| 2068 |
+
"train_batch_size": 5,
|
| 2069 |
+
"trial_name": null,
|
| 2070 |
+
"trial_params": null
|
| 2071 |
+
}
|