Augusto777
commited on
Commit
•
3d9594e
1
Parent(s):
e30a260
End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jun23_14-23-14_DESKTOP-SKBE9FB/events.out.tfevents.1719174926.DESKTOP-SKBE9FB.14100.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +1614 -0
README.md
CHANGED
@@ -22,7 +22,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.8913043478260869
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.4109
|
36 |
+
- Accuracy: 0.8913
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 39.61,
|
3 |
+
"eval_accuracy": 0.8913043478260869,
|
4 |
+
"eval_loss": 0.41094961762428284,
|
5 |
+
"eval_runtime": 1.1432,
|
6 |
+
"eval_samples_per_second": 40.238,
|
7 |
+
"eval_steps_per_second": 5.248,
|
8 |
+
"train_loss": 0.19185902697545495,
|
9 |
+
"train_runtime": 686.8615,
|
10 |
+
"train_samples_per_second": 47.695,
|
11 |
+
"train_steps_per_second": 2.97
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 39.61,
|
3 |
+
"eval_accuracy": 0.8913043478260869,
|
4 |
+
"eval_loss": 0.41094961762428284,
|
5 |
+
"eval_runtime": 1.1432,
|
6 |
+
"eval_samples_per_second": 40.238,
|
7 |
+
"eval_steps_per_second": 5.248
|
8 |
+
}
|
runs/Jun23_14-23-14_DESKTOP-SKBE9FB/events.out.tfevents.1719174926.DESKTOP-SKBE9FB.14100.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e74aa4b8b7f9873bcd64101e557ee50a7098a509ea7f0bac9d9a653cf6b2f842
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 39.61,
|
3 |
+
"train_loss": 0.19185902697545495,
|
4 |
+
"train_runtime": 686.8615,
|
5 |
+
"train_samples_per_second": 47.695,
|
6 |
+
"train_steps_per_second": 2.97
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1614 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8913043478260869,
|
3 |
+
"best_model_checkpoint": "vit-base-patch16-224-ve-U13b-80R\\checkpoint-257",
|
4 |
+
"epoch": 39.61165048543689,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2040,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.19,
|
13 |
+
"learning_rate": 5.392156862745098e-06,
|
14 |
+
"loss": 1.3862,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.39,
|
19 |
+
"learning_rate": 1.0784313725490196e-05,
|
20 |
+
"loss": 1.3853,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.58,
|
25 |
+
"learning_rate": 1.6176470588235296e-05,
|
26 |
+
"loss": 1.3787,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.78,
|
31 |
+
"learning_rate": 2.156862745098039e-05,
|
32 |
+
"loss": 1.3618,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.97,
|
37 |
+
"learning_rate": 2.696078431372549e-05,
|
38 |
+
"loss": 1.3158,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.99,
|
43 |
+
"eval_accuracy": 0.34782608695652173,
|
44 |
+
"eval_loss": 1.2967053651809692,
|
45 |
+
"eval_runtime": 0.8138,
|
46 |
+
"eval_samples_per_second": 56.527,
|
47 |
+
"eval_steps_per_second": 7.373,
|
48 |
+
"step": 51
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.17,
|
52 |
+
"learning_rate": 3.235294117647059e-05,
|
53 |
+
"loss": 1.2679,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.36,
|
58 |
+
"learning_rate": 3.774509803921569e-05,
|
59 |
+
"loss": 1.1853,
|
60 |
+
"step": 70
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.55,
|
64 |
+
"learning_rate": 4.313725490196078e-05,
|
65 |
+
"loss": 1.1516,
|
66 |
+
"step": 80
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.75,
|
70 |
+
"learning_rate": 4.8529411764705885e-05,
|
71 |
+
"loss": 1.0156,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.94,
|
76 |
+
"learning_rate": 5.392156862745098e-05,
|
77 |
+
"loss": 1.0472,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 2.0,
|
82 |
+
"eval_accuracy": 0.5,
|
83 |
+
"eval_loss": 0.9693781137466431,
|
84 |
+
"eval_runtime": 0.8345,
|
85 |
+
"eval_samples_per_second": 55.124,
|
86 |
+
"eval_steps_per_second": 7.19,
|
87 |
+
"step": 103
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.14,
|
91 |
+
"learning_rate": 5.477296181630547e-05,
|
92 |
+
"loss": 0.9316,
|
93 |
+
"step": 110
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.33,
|
97 |
+
"learning_rate": 5.448916408668731e-05,
|
98 |
+
"loss": 0.9232,
|
99 |
+
"step": 120
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.52,
|
103 |
+
"learning_rate": 5.4205366357069146e-05,
|
104 |
+
"loss": 0.8016,
|
105 |
+
"step": 130
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.72,
|
109 |
+
"learning_rate": 5.392156862745098e-05,
|
110 |
+
"loss": 0.7189,
|
111 |
+
"step": 140
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.91,
|
115 |
+
"learning_rate": 5.363777089783282e-05,
|
116 |
+
"loss": 0.6641,
|
117 |
+
"step": 150
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 2.99,
|
121 |
+
"eval_accuracy": 0.7391304347826086,
|
122 |
+
"eval_loss": 0.7911404371261597,
|
123 |
+
"eval_runtime": 0.84,
|
124 |
+
"eval_samples_per_second": 54.763,
|
125 |
+
"eval_steps_per_second": 7.143,
|
126 |
+
"step": 154
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 3.11,
|
130 |
+
"learning_rate": 5.3353973168214655e-05,
|
131 |
+
"loss": 0.7832,
|
132 |
+
"step": 160
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 3.3,
|
136 |
+
"learning_rate": 5.3070175438596496e-05,
|
137 |
+
"loss": 0.6528,
|
138 |
+
"step": 170
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 3.5,
|
142 |
+
"learning_rate": 5.278637770897833e-05,
|
143 |
+
"loss": 0.5867,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.69,
|
148 |
+
"learning_rate": 5.2502579979360165e-05,
|
149 |
+
"loss": 0.5782,
|
150 |
+
"step": 190
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 3.88,
|
154 |
+
"learning_rate": 5.2218782249742006e-05,
|
155 |
+
"loss": 0.5615,
|
156 |
+
"step": 200
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.0,
|
160 |
+
"eval_accuracy": 0.7391304347826086,
|
161 |
+
"eval_loss": 0.6850225329399109,
|
162 |
+
"eval_runtime": 0.8282,
|
163 |
+
"eval_samples_per_second": 55.544,
|
164 |
+
"eval_steps_per_second": 7.245,
|
165 |
+
"step": 206
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 4.08,
|
169 |
+
"learning_rate": 5.193498452012384e-05,
|
170 |
+
"loss": 0.3783,
|
171 |
+
"step": 210
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 4.27,
|
175 |
+
"learning_rate": 5.165118679050568e-05,
|
176 |
+
"loss": 0.4005,
|
177 |
+
"step": 220
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 4.47,
|
181 |
+
"learning_rate": 5.1367389060887515e-05,
|
182 |
+
"loss": 0.4965,
|
183 |
+
"step": 230
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 4.66,
|
187 |
+
"learning_rate": 5.108359133126935e-05,
|
188 |
+
"loss": 0.4172,
|
189 |
+
"step": 240
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 4.85,
|
193 |
+
"learning_rate": 5.079979360165119e-05,
|
194 |
+
"loss": 0.3458,
|
195 |
+
"step": 250
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 4.99,
|
199 |
+
"eval_accuracy": 0.8913043478260869,
|
200 |
+
"eval_loss": 0.41094961762428284,
|
201 |
+
"eval_runtime": 0.8216,
|
202 |
+
"eval_samples_per_second": 55.986,
|
203 |
+
"eval_steps_per_second": 7.302,
|
204 |
+
"step": 257
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 5.05,
|
208 |
+
"learning_rate": 5.0515995872033025e-05,
|
209 |
+
"loss": 0.3214,
|
210 |
+
"step": 260
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 5.24,
|
214 |
+
"learning_rate": 5.023219814241486e-05,
|
215 |
+
"loss": 0.2086,
|
216 |
+
"step": 270
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 5.44,
|
220 |
+
"learning_rate": 4.99484004127967e-05,
|
221 |
+
"loss": 0.2583,
|
222 |
+
"step": 280
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 5.63,
|
226 |
+
"learning_rate": 4.9664602683178534e-05,
|
227 |
+
"loss": 0.3473,
|
228 |
+
"step": 290
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 5.83,
|
232 |
+
"learning_rate": 4.9380804953560375e-05,
|
233 |
+
"loss": 0.3156,
|
234 |
+
"step": 300
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 6.0,
|
238 |
+
"eval_accuracy": 0.8043478260869565,
|
239 |
+
"eval_loss": 0.521323025226593,
|
240 |
+
"eval_runtime": 0.8248,
|
241 |
+
"eval_samples_per_second": 55.773,
|
242 |
+
"eval_steps_per_second": 7.275,
|
243 |
+
"step": 309
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 6.02,
|
247 |
+
"learning_rate": 4.909700722394221e-05,
|
248 |
+
"loss": 0.2727,
|
249 |
+
"step": 310
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 6.21,
|
253 |
+
"learning_rate": 4.8813209494324044e-05,
|
254 |
+
"loss": 0.2321,
|
255 |
+
"step": 320
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 6.41,
|
259 |
+
"learning_rate": 4.8529411764705885e-05,
|
260 |
+
"loss": 0.32,
|
261 |
+
"step": 330
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 6.6,
|
265 |
+
"learning_rate": 4.824561403508772e-05,
|
266 |
+
"loss": 0.2619,
|
267 |
+
"step": 340
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 6.8,
|
271 |
+
"learning_rate": 4.796181630546956e-05,
|
272 |
+
"loss": 0.2209,
|
273 |
+
"step": 350
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 6.99,
|
277 |
+
"learning_rate": 4.7678018575851394e-05,
|
278 |
+
"loss": 0.141,
|
279 |
+
"step": 360
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 6.99,
|
283 |
+
"eval_accuracy": 0.8478260869565217,
|
284 |
+
"eval_loss": 0.479253351688385,
|
285 |
+
"eval_runtime": 0.8312,
|
286 |
+
"eval_samples_per_second": 55.343,
|
287 |
+
"eval_steps_per_second": 7.219,
|
288 |
+
"step": 360
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 7.18,
|
292 |
+
"learning_rate": 4.739422084623323e-05,
|
293 |
+
"loss": 0.2029,
|
294 |
+
"step": 370
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 7.38,
|
298 |
+
"learning_rate": 4.711042311661507e-05,
|
299 |
+
"loss": 0.1304,
|
300 |
+
"step": 380
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 7.57,
|
304 |
+
"learning_rate": 4.6826625386996904e-05,
|
305 |
+
"loss": 0.2513,
|
306 |
+
"step": 390
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 7.77,
|
310 |
+
"learning_rate": 4.6542827657378745e-05,
|
311 |
+
"loss": 0.4012,
|
312 |
+
"step": 400
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 7.96,
|
316 |
+
"learning_rate": 4.625902992776058e-05,
|
317 |
+
"loss": 0.2016,
|
318 |
+
"step": 410
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 8.0,
|
322 |
+
"eval_accuracy": 0.782608695652174,
|
323 |
+
"eval_loss": 0.6031002402305603,
|
324 |
+
"eval_runtime": 0.8127,
|
325 |
+
"eval_samples_per_second": 56.599,
|
326 |
+
"eval_steps_per_second": 7.382,
|
327 |
+
"step": 412
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 8.16,
|
331 |
+
"learning_rate": 4.597523219814241e-05,
|
332 |
+
"loss": 0.1607,
|
333 |
+
"step": 420
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 8.35,
|
337 |
+
"learning_rate": 4.5691434468524254e-05,
|
338 |
+
"loss": 0.1594,
|
339 |
+
"step": 430
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 8.54,
|
343 |
+
"learning_rate": 4.540763673890609e-05,
|
344 |
+
"loss": 0.1961,
|
345 |
+
"step": 440
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 8.74,
|
349 |
+
"learning_rate": 4.512383900928793e-05,
|
350 |
+
"loss": 0.1797,
|
351 |
+
"step": 450
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 8.93,
|
355 |
+
"learning_rate": 4.4840041279669764e-05,
|
356 |
+
"loss": 0.2444,
|
357 |
+
"step": 460
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 8.99,
|
361 |
+
"eval_accuracy": 0.8043478260869565,
|
362 |
+
"eval_loss": 0.7324287295341492,
|
363 |
+
"eval_runtime": 0.8159,
|
364 |
+
"eval_samples_per_second": 56.383,
|
365 |
+
"eval_steps_per_second": 7.354,
|
366 |
+
"step": 463
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 9.13,
|
370 |
+
"learning_rate": 4.45562435500516e-05,
|
371 |
+
"loss": 0.1566,
|
372 |
+
"step": 470
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 9.32,
|
376 |
+
"learning_rate": 4.427244582043344e-05,
|
377 |
+
"loss": 0.1592,
|
378 |
+
"step": 480
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 9.51,
|
382 |
+
"learning_rate": 4.398864809081527e-05,
|
383 |
+
"loss": 0.2563,
|
384 |
+
"step": 490
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 9.71,
|
388 |
+
"learning_rate": 4.3704850361197114e-05,
|
389 |
+
"loss": 0.104,
|
390 |
+
"step": 500
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 9.9,
|
394 |
+
"learning_rate": 4.342105263157895e-05,
|
395 |
+
"loss": 0.1501,
|
396 |
+
"step": 510
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 10.0,
|
400 |
+
"eval_accuracy": 0.8043478260869565,
|
401 |
+
"eval_loss": 0.6391687989234924,
|
402 |
+
"eval_runtime": 0.8212,
|
403 |
+
"eval_samples_per_second": 56.018,
|
404 |
+
"eval_steps_per_second": 7.307,
|
405 |
+
"step": 515
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 10.1,
|
409 |
+
"learning_rate": 4.313725490196078e-05,
|
410 |
+
"loss": 0.0907,
|
411 |
+
"step": 520
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 10.29,
|
415 |
+
"learning_rate": 4.2853457172342624e-05,
|
416 |
+
"loss": 0.0734,
|
417 |
+
"step": 530
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 10.49,
|
421 |
+
"learning_rate": 4.2569659442724465e-05,
|
422 |
+
"loss": 0.1692,
|
423 |
+
"step": 540
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 10.68,
|
427 |
+
"learning_rate": 4.22858617131063e-05,
|
428 |
+
"loss": 0.1427,
|
429 |
+
"step": 550
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 10.87,
|
433 |
+
"learning_rate": 4.200206398348813e-05,
|
434 |
+
"loss": 0.1256,
|
435 |
+
"step": 560
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 10.99,
|
439 |
+
"eval_accuracy": 0.782608695652174,
|
440 |
+
"eval_loss": 0.9706407785415649,
|
441 |
+
"eval_runtime": 0.825,
|
442 |
+
"eval_samples_per_second": 55.757,
|
443 |
+
"eval_steps_per_second": 7.273,
|
444 |
+
"step": 566
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 11.07,
|
448 |
+
"learning_rate": 4.171826625386997e-05,
|
449 |
+
"loss": 0.1986,
|
450 |
+
"step": 570
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 11.26,
|
454 |
+
"learning_rate": 4.143446852425181e-05,
|
455 |
+
"loss": 0.1253,
|
456 |
+
"step": 580
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 11.46,
|
460 |
+
"learning_rate": 4.115067079463365e-05,
|
461 |
+
"loss": 0.0655,
|
462 |
+
"step": 590
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 11.65,
|
466 |
+
"learning_rate": 4.0866873065015484e-05,
|
467 |
+
"loss": 0.2128,
|
468 |
+
"step": 600
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 11.84,
|
472 |
+
"learning_rate": 4.058307533539732e-05,
|
473 |
+
"loss": 0.2421,
|
474 |
+
"step": 610
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 12.0,
|
478 |
+
"eval_accuracy": 0.782608695652174,
|
479 |
+
"eval_loss": 0.8059179186820984,
|
480 |
+
"eval_runtime": 0.8603,
|
481 |
+
"eval_samples_per_second": 53.47,
|
482 |
+
"eval_steps_per_second": 6.974,
|
483 |
+
"step": 618
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 12.04,
|
487 |
+
"learning_rate": 4.029927760577915e-05,
|
488 |
+
"loss": 0.0782,
|
489 |
+
"step": 620
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 12.23,
|
493 |
+
"learning_rate": 4.001547987616099e-05,
|
494 |
+
"loss": 0.1387,
|
495 |
+
"step": 630
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 12.43,
|
499 |
+
"learning_rate": 3.9731682146542834e-05,
|
500 |
+
"loss": 0.1819,
|
501 |
+
"step": 640
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 12.62,
|
505 |
+
"learning_rate": 3.944788441692467e-05,
|
506 |
+
"loss": 0.1062,
|
507 |
+
"step": 650
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 12.82,
|
511 |
+
"learning_rate": 3.91640866873065e-05,
|
512 |
+
"loss": 0.103,
|
513 |
+
"step": 660
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 12.99,
|
517 |
+
"eval_accuracy": 0.8478260869565217,
|
518 |
+
"eval_loss": 0.7600762844085693,
|
519 |
+
"eval_runtime": 0.8507,
|
520 |
+
"eval_samples_per_second": 54.072,
|
521 |
+
"eval_steps_per_second": 7.053,
|
522 |
+
"step": 669
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 13.01,
|
526 |
+
"learning_rate": 3.888028895768834e-05,
|
527 |
+
"loss": 0.1041,
|
528 |
+
"step": 670
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 13.2,
|
532 |
+
"learning_rate": 3.859649122807018e-05,
|
533 |
+
"loss": 0.0645,
|
534 |
+
"step": 680
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 13.4,
|
538 |
+
"learning_rate": 3.831269349845202e-05,
|
539 |
+
"loss": 0.206,
|
540 |
+
"step": 690
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 13.59,
|
544 |
+
"learning_rate": 3.802889576883385e-05,
|
545 |
+
"loss": 0.186,
|
546 |
+
"step": 700
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 13.79,
|
550 |
+
"learning_rate": 3.774509803921569e-05,
|
551 |
+
"loss": 0.1477,
|
552 |
+
"step": 710
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 13.98,
|
556 |
+
"learning_rate": 3.746130030959752e-05,
|
557 |
+
"loss": 0.1353,
|
558 |
+
"step": 720
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 14.0,
|
562 |
+
"eval_accuracy": 0.7391304347826086,
|
563 |
+
"eval_loss": 1.1985808610916138,
|
564 |
+
"eval_runtime": 0.8491,
|
565 |
+
"eval_samples_per_second": 54.175,
|
566 |
+
"eval_steps_per_second": 7.066,
|
567 |
+
"step": 721
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 14.17,
|
571 |
+
"learning_rate": 3.7177502579979356e-05,
|
572 |
+
"loss": 0.2221,
|
573 |
+
"step": 730
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 14.37,
|
577 |
+
"learning_rate": 3.6893704850361204e-05,
|
578 |
+
"loss": 0.0837,
|
579 |
+
"step": 740
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 14.56,
|
583 |
+
"learning_rate": 3.660990712074304e-05,
|
584 |
+
"loss": 0.0987,
|
585 |
+
"step": 750
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 14.76,
|
589 |
+
"learning_rate": 3.632610939112487e-05,
|
590 |
+
"loss": 0.0763,
|
591 |
+
"step": 760
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 14.95,
|
595 |
+
"learning_rate": 3.6042311661506706e-05,
|
596 |
+
"loss": 0.1095,
|
597 |
+
"step": 770
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 14.99,
|
601 |
+
"eval_accuracy": 0.7608695652173914,
|
602 |
+
"eval_loss": 1.0278509855270386,
|
603 |
+
"eval_runtime": 0.9014,
|
604 |
+
"eval_samples_per_second": 51.033,
|
605 |
+
"eval_steps_per_second": 6.656,
|
606 |
+
"step": 772
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 15.15,
|
610 |
+
"learning_rate": 3.575851393188854e-05,
|
611 |
+
"loss": 0.1104,
|
612 |
+
"step": 780
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 15.34,
|
616 |
+
"learning_rate": 3.547471620227039e-05,
|
617 |
+
"loss": 0.1727,
|
618 |
+
"step": 790
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 15.53,
|
622 |
+
"learning_rate": 3.519091847265222e-05,
|
623 |
+
"loss": 0.068,
|
624 |
+
"step": 800
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 15.73,
|
628 |
+
"learning_rate": 3.490712074303406e-05,
|
629 |
+
"loss": 0.0508,
|
630 |
+
"step": 810
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 15.92,
|
634 |
+
"learning_rate": 3.462332301341589e-05,
|
635 |
+
"loss": 0.065,
|
636 |
+
"step": 820
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 16.0,
|
640 |
+
"eval_accuracy": 0.6956521739130435,
|
641 |
+
"eval_loss": 1.2042629718780518,
|
642 |
+
"eval_runtime": 0.8099,
|
643 |
+
"eval_samples_per_second": 56.797,
|
644 |
+
"eval_steps_per_second": 7.408,
|
645 |
+
"step": 824
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 16.12,
|
649 |
+
"learning_rate": 3.4339525283797725e-05,
|
650 |
+
"loss": 0.105,
|
651 |
+
"step": 830
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 16.31,
|
655 |
+
"learning_rate": 3.405572755417957e-05,
|
656 |
+
"loss": 0.0608,
|
657 |
+
"step": 840
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 16.5,
|
661 |
+
"learning_rate": 3.377192982456141e-05,
|
662 |
+
"loss": 0.0378,
|
663 |
+
"step": 850
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 16.7,
|
667 |
+
"learning_rate": 3.348813209494324e-05,
|
668 |
+
"loss": 0.0266,
|
669 |
+
"step": 860
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 16.89,
|
673 |
+
"learning_rate": 3.3204334365325076e-05,
|
674 |
+
"loss": 0.1777,
|
675 |
+
"step": 870
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 16.99,
|
679 |
+
"eval_accuracy": 0.8043478260869565,
|
680 |
+
"eval_loss": 0.9778602719306946,
|
681 |
+
"eval_runtime": 0.9033,
|
682 |
+
"eval_samples_per_second": 50.924,
|
683 |
+
"eval_steps_per_second": 6.642,
|
684 |
+
"step": 875
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 17.09,
|
688 |
+
"learning_rate": 3.292053663570691e-05,
|
689 |
+
"loss": 0.1146,
|
690 |
+
"step": 880
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 17.28,
|
694 |
+
"learning_rate": 3.263673890608876e-05,
|
695 |
+
"loss": 0.13,
|
696 |
+
"step": 890
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 17.48,
|
700 |
+
"learning_rate": 3.235294117647059e-05,
|
701 |
+
"loss": 0.0867,
|
702 |
+
"step": 900
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 17.67,
|
706 |
+
"learning_rate": 3.2069143446852426e-05,
|
707 |
+
"loss": 0.0915,
|
708 |
+
"step": 910
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 17.86,
|
712 |
+
"learning_rate": 3.178534571723426e-05,
|
713 |
+
"loss": 0.0813,
|
714 |
+
"step": 920
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 18.0,
|
718 |
+
"eval_accuracy": 0.7391304347826086,
|
719 |
+
"eval_loss": 1.3356212377548218,
|
720 |
+
"eval_runtime": 0.8192,
|
721 |
+
"eval_samples_per_second": 56.153,
|
722 |
+
"eval_steps_per_second": 7.324,
|
723 |
+
"step": 927
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 18.06,
|
727 |
+
"learning_rate": 3.1501547987616095e-05,
|
728 |
+
"loss": 0.1621,
|
729 |
+
"step": 930
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 18.25,
|
733 |
+
"learning_rate": 3.121775025799794e-05,
|
734 |
+
"loss": 0.0286,
|
735 |
+
"step": 940
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 18.45,
|
739 |
+
"learning_rate": 3.093395252837978e-05,
|
740 |
+
"loss": 0.1057,
|
741 |
+
"step": 950
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 18.64,
|
745 |
+
"learning_rate": 3.065015479876161e-05,
|
746 |
+
"loss": 0.0561,
|
747 |
+
"step": 960
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 18.83,
|
751 |
+
"learning_rate": 3.0366357069143445e-05,
|
752 |
+
"loss": 0.2552,
|
753 |
+
"step": 970
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 18.99,
|
757 |
+
"eval_accuracy": 0.8260869565217391,
|
758 |
+
"eval_loss": 0.8482556343078613,
|
759 |
+
"eval_runtime": 0.8118,
|
760 |
+
"eval_samples_per_second": 56.668,
|
761 |
+
"eval_steps_per_second": 7.391,
|
762 |
+
"step": 978
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 19.03,
|
766 |
+
"learning_rate": 3.0082559339525283e-05,
|
767 |
+
"loss": 0.0844,
|
768 |
+
"step": 980
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 19.22,
|
772 |
+
"learning_rate": 2.9798761609907124e-05,
|
773 |
+
"loss": 0.0336,
|
774 |
+
"step": 990
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 19.42,
|
778 |
+
"learning_rate": 2.9514963880288958e-05,
|
779 |
+
"loss": 0.0222,
|
780 |
+
"step": 1000
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 19.61,
|
784 |
+
"learning_rate": 2.9231166150670796e-05,
|
785 |
+
"loss": 0.1046,
|
786 |
+
"step": 1010
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 19.81,
|
790 |
+
"learning_rate": 2.894736842105263e-05,
|
791 |
+
"loss": 0.0061,
|
792 |
+
"step": 1020
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 20.0,
|
796 |
+
"learning_rate": 2.8663570691434468e-05,
|
797 |
+
"loss": 0.0941,
|
798 |
+
"step": 1030
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 20.0,
|
802 |
+
"eval_accuracy": 0.8695652173913043,
|
803 |
+
"eval_loss": 0.7106134295463562,
|
804 |
+
"eval_runtime": 0.8867,
|
805 |
+
"eval_samples_per_second": 51.875,
|
806 |
+
"eval_steps_per_second": 6.766,
|
807 |
+
"step": 1030
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 20.19,
|
811 |
+
"learning_rate": 2.837977296181631e-05,
|
812 |
+
"loss": 0.1085,
|
813 |
+
"step": 1040
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 20.39,
|
817 |
+
"learning_rate": 2.8095975232198143e-05,
|
818 |
+
"loss": 0.0879,
|
819 |
+
"step": 1050
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 20.58,
|
823 |
+
"learning_rate": 2.781217750257998e-05,
|
824 |
+
"loss": 0.0628,
|
825 |
+
"step": 1060
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 20.78,
|
829 |
+
"learning_rate": 2.7528379772961815e-05,
|
830 |
+
"loss": 0.1618,
|
831 |
+
"step": 1070
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 20.97,
|
835 |
+
"learning_rate": 2.7244582043343656e-05,
|
836 |
+
"loss": 0.0486,
|
837 |
+
"step": 1080
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 20.99,
|
841 |
+
"eval_accuracy": 0.8260869565217391,
|
842 |
+
"eval_loss": 0.8358815908432007,
|
843 |
+
"eval_runtime": 0.8852,
|
844 |
+
"eval_samples_per_second": 51.968,
|
845 |
+
"eval_steps_per_second": 6.778,
|
846 |
+
"step": 1081
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 21.17,
|
850 |
+
"learning_rate": 2.696078431372549e-05,
|
851 |
+
"loss": 0.0991,
|
852 |
+
"step": 1090
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 21.36,
|
856 |
+
"learning_rate": 2.6676986584107328e-05,
|
857 |
+
"loss": 0.0398,
|
858 |
+
"step": 1100
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 21.55,
|
862 |
+
"learning_rate": 2.6393188854489165e-05,
|
863 |
+
"loss": 0.0418,
|
864 |
+
"step": 1110
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 21.75,
|
868 |
+
"learning_rate": 2.6109391124871003e-05,
|
869 |
+
"loss": 0.1183,
|
870 |
+
"step": 1120
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 21.94,
|
874 |
+
"learning_rate": 2.582559339525284e-05,
|
875 |
+
"loss": 0.0361,
|
876 |
+
"step": 1130
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 22.0,
|
880 |
+
"eval_accuracy": 0.8260869565217391,
|
881 |
+
"eval_loss": 0.8709820508956909,
|
882 |
+
"eval_runtime": 0.9357,
|
883 |
+
"eval_samples_per_second": 49.161,
|
884 |
+
"eval_steps_per_second": 6.412,
|
885 |
+
"step": 1133
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 22.14,
|
889 |
+
"learning_rate": 2.5541795665634675e-05,
|
890 |
+
"loss": 0.0933,
|
891 |
+
"step": 1140
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 22.33,
|
895 |
+
"learning_rate": 2.5257997936016512e-05,
|
896 |
+
"loss": 0.0794,
|
897 |
+
"step": 1150
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 22.52,
|
901 |
+
"learning_rate": 2.497420020639835e-05,
|
902 |
+
"loss": 0.0888,
|
903 |
+
"step": 1160
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 22.72,
|
907 |
+
"learning_rate": 2.4690402476780188e-05,
|
908 |
+
"loss": 0.0743,
|
909 |
+
"step": 1170
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 22.91,
|
913 |
+
"learning_rate": 2.4406604747162022e-05,
|
914 |
+
"loss": 0.0361,
|
915 |
+
"step": 1180
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 22.99,
|
919 |
+
"eval_accuracy": 0.8043478260869565,
|
920 |
+
"eval_loss": 1.0301445722579956,
|
921 |
+
"eval_runtime": 0.8187,
|
922 |
+
"eval_samples_per_second": 56.187,
|
923 |
+
"eval_steps_per_second": 7.329,
|
924 |
+
"step": 1184
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 23.11,
|
928 |
+
"learning_rate": 2.412280701754386e-05,
|
929 |
+
"loss": 0.0157,
|
930 |
+
"step": 1190
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 23.3,
|
934 |
+
"learning_rate": 2.3839009287925697e-05,
|
935 |
+
"loss": 0.0982,
|
936 |
+
"step": 1200
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 23.5,
|
940 |
+
"learning_rate": 2.3555211558307535e-05,
|
941 |
+
"loss": 0.0532,
|
942 |
+
"step": 1210
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 23.69,
|
946 |
+
"learning_rate": 2.3271413828689372e-05,
|
947 |
+
"loss": 0.1318,
|
948 |
+
"step": 1220
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 23.88,
|
952 |
+
"learning_rate": 2.2987616099071207e-05,
|
953 |
+
"loss": 0.0136,
|
954 |
+
"step": 1230
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 24.0,
|
958 |
+
"eval_accuracy": 0.8260869565217391,
|
959 |
+
"eval_loss": 0.9014785885810852,
|
960 |
+
"eval_runtime": 0.8125,
|
961 |
+
"eval_samples_per_second": 56.618,
|
962 |
+
"eval_steps_per_second": 7.385,
|
963 |
+
"step": 1236
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 24.08,
|
967 |
+
"learning_rate": 2.2703818369453044e-05,
|
968 |
+
"loss": 0.0498,
|
969 |
+
"step": 1240
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 24.27,
|
973 |
+
"learning_rate": 2.2420020639834882e-05,
|
974 |
+
"loss": 0.1254,
|
975 |
+
"step": 1250
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 24.47,
|
979 |
+
"learning_rate": 2.213622291021672e-05,
|
980 |
+
"loss": 0.0627,
|
981 |
+
"step": 1260
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 24.66,
|
985 |
+
"learning_rate": 2.1852425180598557e-05,
|
986 |
+
"loss": 0.0623,
|
987 |
+
"step": 1270
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 24.85,
|
991 |
+
"learning_rate": 2.156862745098039e-05,
|
992 |
+
"loss": 0.1441,
|
993 |
+
"step": 1280
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 24.99,
|
997 |
+
"eval_accuracy": 0.8043478260869565,
|
998 |
+
"eval_loss": 0.9957734942436218,
|
999 |
+
"eval_runtime": 0.9088,
|
1000 |
+
"eval_samples_per_second": 50.618,
|
1001 |
+
"eval_steps_per_second": 6.602,
|
1002 |
+
"step": 1287
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 25.05,
|
1006 |
+
"learning_rate": 2.1284829721362232e-05,
|
1007 |
+
"loss": 0.1111,
|
1008 |
+
"step": 1290
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 25.24,
|
1012 |
+
"learning_rate": 2.1001031991744067e-05,
|
1013 |
+
"loss": 0.1302,
|
1014 |
+
"step": 1300
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 25.44,
|
1018 |
+
"learning_rate": 2.0717234262125904e-05,
|
1019 |
+
"loss": 0.0337,
|
1020 |
+
"step": 1310
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 25.63,
|
1024 |
+
"learning_rate": 2.0433436532507742e-05,
|
1025 |
+
"loss": 0.1372,
|
1026 |
+
"step": 1320
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 25.83,
|
1030 |
+
"learning_rate": 2.0149638802889576e-05,
|
1031 |
+
"loss": 0.0181,
|
1032 |
+
"step": 1330
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 26.0,
|
1036 |
+
"eval_accuracy": 0.782608695652174,
|
1037 |
+
"eval_loss": 1.079309105873108,
|
1038 |
+
"eval_runtime": 0.8523,
|
1039 |
+
"eval_samples_per_second": 53.969,
|
1040 |
+
"eval_steps_per_second": 7.039,
|
1041 |
+
"step": 1339
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 26.02,
|
1045 |
+
"learning_rate": 1.9865841073271417e-05,
|
1046 |
+
"loss": 0.0089,
|
1047 |
+
"step": 1340
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 26.21,
|
1051 |
+
"learning_rate": 1.958204334365325e-05,
|
1052 |
+
"loss": 0.0692,
|
1053 |
+
"step": 1350
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 26.41,
|
1057 |
+
"learning_rate": 1.929824561403509e-05,
|
1058 |
+
"loss": 0.0977,
|
1059 |
+
"step": 1360
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 26.6,
|
1063 |
+
"learning_rate": 1.9014447884416927e-05,
|
1064 |
+
"loss": 0.061,
|
1065 |
+
"step": 1370
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 26.8,
|
1069 |
+
"learning_rate": 1.873065015479876e-05,
|
1070 |
+
"loss": 0.1206,
|
1071 |
+
"step": 1380
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 26.99,
|
1075 |
+
"learning_rate": 1.8446852425180602e-05,
|
1076 |
+
"loss": 0.0612,
|
1077 |
+
"step": 1390
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 26.99,
|
1081 |
+
"eval_accuracy": 0.8043478260869565,
|
1082 |
+
"eval_loss": 0.9677725434303284,
|
1083 |
+
"eval_runtime": 0.8237,
|
1084 |
+
"eval_samples_per_second": 55.849,
|
1085 |
+
"eval_steps_per_second": 7.285,
|
1086 |
+
"step": 1390
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 27.18,
|
1090 |
+
"learning_rate": 1.8163054695562436e-05,
|
1091 |
+
"loss": 0.0322,
|
1092 |
+
"step": 1400
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 27.38,
|
1096 |
+
"learning_rate": 1.787925696594427e-05,
|
1097 |
+
"loss": 0.0801,
|
1098 |
+
"step": 1410
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 27.57,
|
1102 |
+
"learning_rate": 1.759545923632611e-05,
|
1103 |
+
"loss": 0.0297,
|
1104 |
+
"step": 1420
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 27.77,
|
1108 |
+
"learning_rate": 1.7311661506707946e-05,
|
1109 |
+
"loss": 0.0029,
|
1110 |
+
"step": 1430
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 27.96,
|
1114 |
+
"learning_rate": 1.7027863777089787e-05,
|
1115 |
+
"loss": 0.0814,
|
1116 |
+
"step": 1440
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 28.0,
|
1120 |
+
"eval_accuracy": 0.782608695652174,
|
1121 |
+
"eval_loss": 1.0320191383361816,
|
1122 |
+
"eval_runtime": 0.8644,
|
1123 |
+
"eval_samples_per_second": 53.215,
|
1124 |
+
"eval_steps_per_second": 6.941,
|
1125 |
+
"step": 1442
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 28.16,
|
1129 |
+
"learning_rate": 1.674406604747162e-05,
|
1130 |
+
"loss": 0.0618,
|
1131 |
+
"step": 1450
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 28.35,
|
1135 |
+
"learning_rate": 1.6460268317853455e-05,
|
1136 |
+
"loss": 0.0544,
|
1137 |
+
"step": 1460
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 28.54,
|
1141 |
+
"learning_rate": 1.6176470588235296e-05,
|
1142 |
+
"loss": 0.0386,
|
1143 |
+
"step": 1470
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 28.74,
|
1147 |
+
"learning_rate": 1.589267285861713e-05,
|
1148 |
+
"loss": 0.0649,
|
1149 |
+
"step": 1480
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 28.93,
|
1153 |
+
"learning_rate": 1.560887512899897e-05,
|
1154 |
+
"loss": 0.0479,
|
1155 |
+
"step": 1490
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 28.99,
|
1159 |
+
"eval_accuracy": 0.782608695652174,
|
1160 |
+
"eval_loss": 1.1844698190689087,
|
1161 |
+
"eval_runtime": 0.95,
|
1162 |
+
"eval_samples_per_second": 48.422,
|
1163 |
+
"eval_steps_per_second": 6.316,
|
1164 |
+
"step": 1493
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 29.13,
|
1168 |
+
"learning_rate": 1.5325077399380806e-05,
|
1169 |
+
"loss": 0.0619,
|
1170 |
+
"step": 1500
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 29.32,
|
1174 |
+
"learning_rate": 1.5041279669762642e-05,
|
1175 |
+
"loss": 0.0879,
|
1176 |
+
"step": 1510
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 29.51,
|
1180 |
+
"learning_rate": 1.4757481940144479e-05,
|
1181 |
+
"loss": 0.0265,
|
1182 |
+
"step": 1520
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 29.71,
|
1186 |
+
"learning_rate": 1.4473684210526315e-05,
|
1187 |
+
"loss": 0.0454,
|
1188 |
+
"step": 1530
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 29.9,
|
1192 |
+
"learning_rate": 1.4189886480908154e-05,
|
1193 |
+
"loss": 0.06,
|
1194 |
+
"step": 1540
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 30.0,
|
1198 |
+
"eval_accuracy": 0.782608695652174,
|
1199 |
+
"eval_loss": 1.2025697231292725,
|
1200 |
+
"eval_runtime": 0.8387,
|
1201 |
+
"eval_samples_per_second": 54.844,
|
1202 |
+
"eval_steps_per_second": 7.154,
|
1203 |
+
"step": 1545
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 30.1,
|
1207 |
+
"learning_rate": 1.390608875128999e-05,
|
1208 |
+
"loss": 0.0116,
|
1209 |
+
"step": 1550
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 30.29,
|
1213 |
+
"learning_rate": 1.3622291021671828e-05,
|
1214 |
+
"loss": 0.0595,
|
1215 |
+
"step": 1560
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 30.49,
|
1219 |
+
"learning_rate": 1.3338493292053664e-05,
|
1220 |
+
"loss": 0.0868,
|
1221 |
+
"step": 1570
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 30.68,
|
1225 |
+
"learning_rate": 1.3054695562435501e-05,
|
1226 |
+
"loss": 0.0212,
|
1227 |
+
"step": 1580
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 30.87,
|
1231 |
+
"learning_rate": 1.2770897832817337e-05,
|
1232 |
+
"loss": 0.0777,
|
1233 |
+
"step": 1590
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 30.99,
|
1237 |
+
"eval_accuracy": 0.782608695652174,
|
1238 |
+
"eval_loss": 1.1574479341506958,
|
1239 |
+
"eval_runtime": 0.8863,
|
1240 |
+
"eval_samples_per_second": 51.899,
|
1241 |
+
"eval_steps_per_second": 6.769,
|
1242 |
+
"step": 1596
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 31.07,
|
1246 |
+
"learning_rate": 1.2487100103199175e-05,
|
1247 |
+
"loss": 0.0554,
|
1248 |
+
"step": 1600
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 31.26,
|
1252 |
+
"learning_rate": 1.2203302373581011e-05,
|
1253 |
+
"loss": 0.0213,
|
1254 |
+
"step": 1610
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 31.46,
|
1258 |
+
"learning_rate": 1.1919504643962849e-05,
|
1259 |
+
"loss": 0.0077,
|
1260 |
+
"step": 1620
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 31.65,
|
1264 |
+
"learning_rate": 1.1635706914344686e-05,
|
1265 |
+
"loss": 0.0406,
|
1266 |
+
"step": 1630
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 31.84,
|
1270 |
+
"learning_rate": 1.1351909184726522e-05,
|
1271 |
+
"loss": 0.0747,
|
1272 |
+
"step": 1640
|
1273 |
+
},
|
1274 |
+
{
|
1275 |
+
"epoch": 32.0,
|
1276 |
+
"eval_accuracy": 0.7608695652173914,
|
1277 |
+
"eval_loss": 1.3103581666946411,
|
1278 |
+
"eval_runtime": 0.8519,
|
1279 |
+
"eval_samples_per_second": 54.0,
|
1280 |
+
"eval_steps_per_second": 7.043,
|
1281 |
+
"step": 1648
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 32.04,
|
1285 |
+
"learning_rate": 1.106811145510836e-05,
|
1286 |
+
"loss": 0.0665,
|
1287 |
+
"step": 1650
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 32.23,
|
1291 |
+
"learning_rate": 1.0784313725490196e-05,
|
1292 |
+
"loss": 0.0245,
|
1293 |
+
"step": 1660
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 32.43,
|
1297 |
+
"learning_rate": 1.0500515995872033e-05,
|
1298 |
+
"loss": 0.0713,
|
1299 |
+
"step": 1670
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 32.62,
|
1303 |
+
"learning_rate": 1.0216718266253871e-05,
|
1304 |
+
"loss": 0.0285,
|
1305 |
+
"step": 1680
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 32.82,
|
1309 |
+
"learning_rate": 9.932920536635709e-06,
|
1310 |
+
"loss": 0.0181,
|
1311 |
+
"step": 1690
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 32.99,
|
1315 |
+
"eval_accuracy": 0.8043478260869565,
|
1316 |
+
"eval_loss": 1.1144654750823975,
|
1317 |
+
"eval_runtime": 0.8141,
|
1318 |
+
"eval_samples_per_second": 56.505,
|
1319 |
+
"eval_steps_per_second": 7.37,
|
1320 |
+
"step": 1699
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 33.01,
|
1324 |
+
"learning_rate": 9.649122807017545e-06,
|
1325 |
+
"loss": 0.0843,
|
1326 |
+
"step": 1700
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 33.2,
|
1330 |
+
"learning_rate": 9.36532507739938e-06,
|
1331 |
+
"loss": 0.06,
|
1332 |
+
"step": 1710
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 33.4,
|
1336 |
+
"learning_rate": 9.081527347781218e-06,
|
1337 |
+
"loss": 0.0857,
|
1338 |
+
"step": 1720
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 33.59,
|
1342 |
+
"learning_rate": 8.797729618163056e-06,
|
1343 |
+
"loss": 0.0588,
|
1344 |
+
"step": 1730
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 33.79,
|
1348 |
+
"learning_rate": 8.513931888544893e-06,
|
1349 |
+
"loss": 0.056,
|
1350 |
+
"step": 1740
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 33.98,
|
1354 |
+
"learning_rate": 8.230134158926728e-06,
|
1355 |
+
"loss": 0.0652,
|
1356 |
+
"step": 1750
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 34.0,
|
1360 |
+
"eval_accuracy": 0.8043478260869565,
|
1361 |
+
"eval_loss": 1.169052243232727,
|
1362 |
+
"eval_runtime": 0.8113,
|
1363 |
+
"eval_samples_per_second": 56.696,
|
1364 |
+
"eval_steps_per_second": 7.395,
|
1365 |
+
"step": 1751
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 34.17,
|
1369 |
+
"learning_rate": 7.946336429308565e-06,
|
1370 |
+
"loss": 0.0934,
|
1371 |
+
"step": 1760
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 34.37,
|
1375 |
+
"learning_rate": 7.662538699690403e-06,
|
1376 |
+
"loss": 0.0226,
|
1377 |
+
"step": 1770
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 34.56,
|
1381 |
+
"learning_rate": 7.3787409700722396e-06,
|
1382 |
+
"loss": 0.0324,
|
1383 |
+
"step": 1780
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 34.76,
|
1387 |
+
"learning_rate": 7.094943240454077e-06,
|
1388 |
+
"loss": 0.0346,
|
1389 |
+
"step": 1790
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 34.95,
|
1393 |
+
"learning_rate": 6.811145510835914e-06,
|
1394 |
+
"loss": 0.0242,
|
1395 |
+
"step": 1800
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 34.99,
|
1399 |
+
"eval_accuracy": 0.8043478260869565,
|
1400 |
+
"eval_loss": 1.241450548171997,
|
1401 |
+
"eval_runtime": 0.7829,
|
1402 |
+
"eval_samples_per_second": 58.754,
|
1403 |
+
"eval_steps_per_second": 7.664,
|
1404 |
+
"step": 1802
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 35.15,
|
1408 |
+
"learning_rate": 6.527347781217751e-06,
|
1409 |
+
"loss": 0.0833,
|
1410 |
+
"step": 1810
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 35.34,
|
1414 |
+
"learning_rate": 6.2435500515995875e-06,
|
1415 |
+
"loss": 0.0109,
|
1416 |
+
"step": 1820
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 35.53,
|
1420 |
+
"learning_rate": 5.959752321981424e-06,
|
1421 |
+
"loss": 0.0282,
|
1422 |
+
"step": 1830
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 35.73,
|
1426 |
+
"learning_rate": 5.675954592363261e-06,
|
1427 |
+
"loss": 0.0117,
|
1428 |
+
"step": 1840
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 35.92,
|
1432 |
+
"learning_rate": 5.392156862745098e-06,
|
1433 |
+
"loss": 0.0043,
|
1434 |
+
"step": 1850
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 36.0,
|
1438 |
+
"eval_accuracy": 0.782608695652174,
|
1439 |
+
"eval_loss": 1.1841026544570923,
|
1440 |
+
"eval_runtime": 0.8263,
|
1441 |
+
"eval_samples_per_second": 55.669,
|
1442 |
+
"eval_steps_per_second": 7.261,
|
1443 |
+
"step": 1854
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 36.12,
|
1447 |
+
"learning_rate": 5.1083591331269355e-06,
|
1448 |
+
"loss": 0.0222,
|
1449 |
+
"step": 1860
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 36.31,
|
1453 |
+
"learning_rate": 4.824561403508772e-06,
|
1454 |
+
"loss": 0.0067,
|
1455 |
+
"step": 1870
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 36.5,
|
1459 |
+
"learning_rate": 4.540763673890609e-06,
|
1460 |
+
"loss": 0.06,
|
1461 |
+
"step": 1880
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 36.7,
|
1465 |
+
"learning_rate": 4.256965944272447e-06,
|
1466 |
+
"loss": 0.1418,
|
1467 |
+
"step": 1890
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 36.89,
|
1471 |
+
"learning_rate": 3.973168214654283e-06,
|
1472 |
+
"loss": 0.0318,
|
1473 |
+
"step": 1900
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 36.99,
|
1477 |
+
"eval_accuracy": 0.8043478260869565,
|
1478 |
+
"eval_loss": 1.2474864721298218,
|
1479 |
+
"eval_runtime": 0.8535,
|
1480 |
+
"eval_samples_per_second": 53.898,
|
1481 |
+
"eval_steps_per_second": 7.03,
|
1482 |
+
"step": 1905
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 37.09,
|
1486 |
+
"learning_rate": 3.6893704850361198e-06,
|
1487 |
+
"loss": 0.0314,
|
1488 |
+
"step": 1910
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 37.28,
|
1492 |
+
"learning_rate": 3.405572755417957e-06,
|
1493 |
+
"loss": 0.0319,
|
1494 |
+
"step": 1920
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 37.48,
|
1498 |
+
"learning_rate": 3.1217750257997938e-06,
|
1499 |
+
"loss": 0.0323,
|
1500 |
+
"step": 1930
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 37.67,
|
1504 |
+
"learning_rate": 2.8379772961816305e-06,
|
1505 |
+
"loss": 0.03,
|
1506 |
+
"step": 1940
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 37.86,
|
1510 |
+
"learning_rate": 2.5541795665634677e-06,
|
1511 |
+
"loss": 0.0092,
|
1512 |
+
"step": 1950
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 38.0,
|
1516 |
+
"eval_accuracy": 0.8043478260869565,
|
1517 |
+
"eval_loss": 1.245222806930542,
|
1518 |
+
"eval_runtime": 0.7782,
|
1519 |
+
"eval_samples_per_second": 59.113,
|
1520 |
+
"eval_steps_per_second": 7.71,
|
1521 |
+
"step": 1957
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 38.06,
|
1525 |
+
"learning_rate": 2.2703818369453045e-06,
|
1526 |
+
"loss": 0.0341,
|
1527 |
+
"step": 1960
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 38.25,
|
1531 |
+
"learning_rate": 1.9865841073271413e-06,
|
1532 |
+
"loss": 0.0439,
|
1533 |
+
"step": 1970
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 38.45,
|
1537 |
+
"learning_rate": 1.7027863777089785e-06,
|
1538 |
+
"loss": 0.0532,
|
1539 |
+
"step": 1980
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 38.64,
|
1543 |
+
"learning_rate": 1.4189886480908153e-06,
|
1544 |
+
"loss": 0.0495,
|
1545 |
+
"step": 1990
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 38.83,
|
1549 |
+
"learning_rate": 1.1351909184726523e-06,
|
1550 |
+
"loss": 0.0194,
|
1551 |
+
"step": 2000
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 38.99,
|
1555 |
+
"eval_accuracy": 0.8043478260869565,
|
1556 |
+
"eval_loss": 1.2395203113555908,
|
1557 |
+
"eval_runtime": 0.8322,
|
1558 |
+
"eval_samples_per_second": 55.275,
|
1559 |
+
"eval_steps_per_second": 7.21,
|
1560 |
+
"step": 2008
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 39.03,
|
1564 |
+
"learning_rate": 8.513931888544892e-07,
|
1565 |
+
"loss": 0.0187,
|
1566 |
+
"step": 2010
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 39.22,
|
1570 |
+
"learning_rate": 5.675954592363261e-07,
|
1571 |
+
"loss": 0.0222,
|
1572 |
+
"step": 2020
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 39.42,
|
1576 |
+
"learning_rate": 2.8379772961816306e-07,
|
1577 |
+
"loss": 0.0755,
|
1578 |
+
"step": 2030
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 39.61,
|
1582 |
+
"learning_rate": 0.0,
|
1583 |
+
"loss": 0.0376,
|
1584 |
+
"step": 2040
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 39.61,
|
1588 |
+
"eval_accuracy": 0.8043478260869565,
|
1589 |
+
"eval_loss": 1.2345207929611206,
|
1590 |
+
"eval_runtime": 0.8062,
|
1591 |
+
"eval_samples_per_second": 57.059,
|
1592 |
+
"eval_steps_per_second": 7.443,
|
1593 |
+
"step": 2040
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 39.61,
|
1597 |
+
"step": 2040,
|
1598 |
+
"total_flos": 2.5142726714989363e+18,
|
1599 |
+
"train_loss": 0.19185902697545495,
|
1600 |
+
"train_runtime": 686.8615,
|
1601 |
+
"train_samples_per_second": 47.695,
|
1602 |
+
"train_steps_per_second": 2.97
|
1603 |
+
}
|
1604 |
+
],
|
1605 |
+
"logging_steps": 10,
|
1606 |
+
"max_steps": 2040,
|
1607 |
+
"num_input_tokens_seen": 0,
|
1608 |
+
"num_train_epochs": 40,
|
1609 |
+
"save_steps": 500,
|
1610 |
+
"total_flos": 2.5142726714989363e+18,
|
1611 |
+
"train_batch_size": 8,
|
1612 |
+
"trial_name": null,
|
1613 |
+
"trial_params": null
|
1614 |
+
}
|