frostsolutions/frost-vision-v2-google_vit-base-patch16-384-v2024-11-10
Browse files- README.md +9 -9
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Nov10_06-44-55_a61ec4b32b41/events.out.tfevents.1731222412.a61ec4b32b41.1365.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1785 -0
README.md
CHANGED
@@ -26,16 +26,16 @@ model-index:
|
|
26 |
metrics:
|
27 |
- name: Accuracy
|
28 |
type: accuracy
|
29 |
-
value: 0.
|
30 |
- name: F1
|
31 |
type: f1
|
32 |
-
value: 0.
|
33 |
- name: Precision
|
34 |
type: precision
|
35 |
-
value: 0.
|
36 |
- name: Recall
|
37 |
type: recall
|
38 |
-
value: 0.
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
45 |
|
46 |
This model is a fine-tuned version of [google/vit-base-patch16-384](https://huggingface.co/google/vit-base-patch16-384) on the webdataset dataset.
|
47 |
It achieves the following results on the evaluation set:
|
48 |
-
- Loss: 0.
|
49 |
-
- Accuracy: 0.
|
50 |
-
- F1: 0.
|
51 |
-
- Precision: 0.
|
52 |
-
- Recall: 0.
|
53 |
|
54 |
## Model description
|
55 |
|
|
|
26 |
metrics:
|
27 |
- name: Accuracy
|
28 |
type: accuracy
|
29 |
+
value: 0.9274647887323944
|
30 |
- name: F1
|
31 |
type: f1
|
32 |
+
value: 0.8186619718309859
|
33 |
- name: Precision
|
34 |
type: precision
|
35 |
+
value: 0.8172231985940246
|
36 |
- name: Recall
|
37 |
type: recall
|
38 |
+
value: 0.8201058201058201
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
45 |
|
46 |
This model is a fine-tuned version of [google/vit-base-patch16-384](https://huggingface.co/google/vit-base-patch16-384) on the webdataset dataset.
|
47 |
It achieves the following results on the evaluation set:
|
48 |
+
- Loss: 0.1847
|
49 |
+
- Accuracy: 0.9275
|
50 |
+
- F1: 0.8187
|
51 |
+
- Precision: 0.8172
|
52 |
+
- Recall: 0.8201
|
53 |
|
54 |
## Model description
|
55 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"eval_accuracy": 0.9274647887323944,
|
4 |
+
"eval_f1": 0.8186619718309859,
|
5 |
+
"eval_loss": 0.18472303450107574,
|
6 |
+
"eval_precision": 0.8172231985940246,
|
7 |
+
"eval_recall": 0.8201058201058201,
|
8 |
+
"eval_runtime": 4.289,
|
9 |
+
"eval_samples_per_second": 66.215,
|
10 |
+
"eval_steps_per_second": 8.393,
|
11 |
+
"total_flos": 7.774335248148726e+18,
|
12 |
+
"train_loss": 0.08187752739294595,
|
13 |
+
"train_runtime": 1287.2767,
|
14 |
+
"train_samples_per_second": 26.428,
|
15 |
+
"train_steps_per_second": 1.655
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"eval_accuracy": 0.9274647887323944,
|
4 |
+
"eval_f1": 0.8186619718309859,
|
5 |
+
"eval_loss": 0.18472303450107574,
|
6 |
+
"eval_precision": 0.8172231985940246,
|
7 |
+
"eval_recall": 0.8201058201058201,
|
8 |
+
"eval_runtime": 4.289,
|
9 |
+
"eval_samples_per_second": 66.215,
|
10 |
+
"eval_steps_per_second": 8.393
|
11 |
+
}
|
runs/Nov10_06-44-55_a61ec4b32b41/events.out.tfevents.1731222412.a61ec4b32b41.1365.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbaca6c6ddfae805d576c7b10c3010d17bfa72a5ec8c6b2f7f27f216084dc00a
|
3 |
+
size 560
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"total_flos": 7.774335248148726e+18,
|
4 |
+
"train_loss": 0.08187752739294595,
|
5 |
+
"train_runtime": 1287.2767,
|
6 |
+
"train_samples_per_second": 26.428,
|
7 |
+
"train_steps_per_second": 1.655
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1785 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.18472303450107574,
|
3 |
+
"best_model_checkpoint": "frost-vision-v2-google_vit-base-patch16-384-v2024-11-10/checkpoint-500",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 2130,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.14084507042253522,
|
13 |
+
"grad_norm": 1.9532430171966553,
|
14 |
+
"learning_rate": 9.389671361502347e-06,
|
15 |
+
"loss": 0.7081,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.28169014084507044,
|
20 |
+
"grad_norm": 1.4905153512954712,
|
21 |
+
"learning_rate": 1.8779342723004694e-05,
|
22 |
+
"loss": 0.5966,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.4225352112676056,
|
27 |
+
"grad_norm": 1.0629397630691528,
|
28 |
+
"learning_rate": 2.8169014084507046e-05,
|
29 |
+
"loss": 0.4634,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.5633802816901409,
|
34 |
+
"grad_norm": 1.1944268941879272,
|
35 |
+
"learning_rate": 3.755868544600939e-05,
|
36 |
+
"loss": 0.4103,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.704225352112676,
|
41 |
+
"grad_norm": 1.0600364208221436,
|
42 |
+
"learning_rate": 4.694835680751174e-05,
|
43 |
+
"loss": 0.3456,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.8450704225352113,
|
48 |
+
"grad_norm": 0.9409961700439453,
|
49 |
+
"learning_rate": 5.633802816901409e-05,
|
50 |
+
"loss": 0.2917,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.9859154929577465,
|
55 |
+
"grad_norm": 0.9866936206817627,
|
56 |
+
"learning_rate": 6.572769953051644e-05,
|
57 |
+
"loss": 0.2536,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.1267605633802817,
|
62 |
+
"grad_norm": 0.8040021657943726,
|
63 |
+
"learning_rate": 7.511737089201878e-05,
|
64 |
+
"loss": 0.236,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.267605633802817,
|
69 |
+
"grad_norm": 0.7174156904220581,
|
70 |
+
"learning_rate": 8.450704225352113e-05,
|
71 |
+
"loss": 0.2305,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.408450704225352,
|
76 |
+
"grad_norm": 1.468618631362915,
|
77 |
+
"learning_rate": 9.389671361502347e-05,
|
78 |
+
"loss": 0.2243,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.408450704225352,
|
83 |
+
"eval_accuracy": 0.9242957746478874,
|
84 |
+
"eval_f1": 0.7981220657276995,
|
85 |
+
"eval_loss": 0.20880411565303802,
|
86 |
+
"eval_precision": 0.8534136546184738,
|
87 |
+
"eval_recall": 0.7495590828924162,
|
88 |
+
"eval_runtime": 4.7453,
|
89 |
+
"eval_samples_per_second": 59.848,
|
90 |
+
"eval_steps_per_second": 7.586,
|
91 |
+
"step": 100
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.5492957746478875,
|
95 |
+
"grad_norm": 1.7064496278762817,
|
96 |
+
"learning_rate": 0.00010328638497652582,
|
97 |
+
"loss": 0.2272,
|
98 |
+
"step": 110
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.6901408450704225,
|
102 |
+
"grad_norm": 0.8617244362831116,
|
103 |
+
"learning_rate": 0.00011267605633802819,
|
104 |
+
"loss": 0.2142,
|
105 |
+
"step": 120
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 1.8309859154929577,
|
109 |
+
"grad_norm": 0.8898526430130005,
|
110 |
+
"learning_rate": 0.00012206572769953053,
|
111 |
+
"loss": 0.2208,
|
112 |
+
"step": 130
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 1.971830985915493,
|
116 |
+
"grad_norm": 1.2177144289016724,
|
117 |
+
"learning_rate": 0.00013145539906103288,
|
118 |
+
"loss": 0.2147,
|
119 |
+
"step": 140
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 2.112676056338028,
|
123 |
+
"grad_norm": 1.7734003067016602,
|
124 |
+
"learning_rate": 0.00014084507042253522,
|
125 |
+
"loss": 0.1993,
|
126 |
+
"step": 150
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 2.2535211267605635,
|
130 |
+
"grad_norm": 0.9507364630699158,
|
131 |
+
"learning_rate": 0.00015023474178403755,
|
132 |
+
"loss": 0.1806,
|
133 |
+
"step": 160
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 2.3943661971830985,
|
137 |
+
"grad_norm": 0.9511057734489441,
|
138 |
+
"learning_rate": 0.00015962441314553992,
|
139 |
+
"loss": 0.1913,
|
140 |
+
"step": 170
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.535211267605634,
|
144 |
+
"grad_norm": 1.419704556465149,
|
145 |
+
"learning_rate": 0.00016901408450704225,
|
146 |
+
"loss": 0.1949,
|
147 |
+
"step": 180
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 2.676056338028169,
|
151 |
+
"grad_norm": 0.8608860373497009,
|
152 |
+
"learning_rate": 0.00017840375586854461,
|
153 |
+
"loss": 0.1907,
|
154 |
+
"step": 190
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 2.816901408450704,
|
158 |
+
"grad_norm": 1.1266043186187744,
|
159 |
+
"learning_rate": 0.00018779342723004695,
|
160 |
+
"loss": 0.2438,
|
161 |
+
"step": 200
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 2.816901408450704,
|
165 |
+
"eval_accuracy": 0.9299295774647888,
|
166 |
+
"eval_f1": 0.8102955195424214,
|
167 |
+
"eval_loss": 0.18185150623321533,
|
168 |
+
"eval_precision": 0.8817427385892116,
|
169 |
+
"eval_recall": 0.7495590828924162,
|
170 |
+
"eval_runtime": 4.6977,
|
171 |
+
"eval_samples_per_second": 60.455,
|
172 |
+
"eval_steps_per_second": 7.663,
|
173 |
+
"step": 200
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 2.9577464788732395,
|
177 |
+
"grad_norm": 0.9358466267585754,
|
178 |
+
"learning_rate": 0.0001971830985915493,
|
179 |
+
"loss": 0.1805,
|
180 |
+
"step": 210
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.0985915492957745,
|
184 |
+
"grad_norm": 0.5238935351371765,
|
185 |
+
"learning_rate": 0.00019926969222743872,
|
186 |
+
"loss": 0.1614,
|
187 |
+
"step": 220
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 3.23943661971831,
|
191 |
+
"grad_norm": 0.8152980208396912,
|
192 |
+
"learning_rate": 0.00019822639540949402,
|
193 |
+
"loss": 0.1632,
|
194 |
+
"step": 230
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.380281690140845,
|
198 |
+
"grad_norm": 0.8670392036437988,
|
199 |
+
"learning_rate": 0.0001971830985915493,
|
200 |
+
"loss": 0.17,
|
201 |
+
"step": 240
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 3.52112676056338,
|
205 |
+
"grad_norm": 0.719203531742096,
|
206 |
+
"learning_rate": 0.0001961398017736046,
|
207 |
+
"loss": 0.1843,
|
208 |
+
"step": 250
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 3.6619718309859155,
|
212 |
+
"grad_norm": 1.1024322509765625,
|
213 |
+
"learning_rate": 0.0001950965049556599,
|
214 |
+
"loss": 0.1843,
|
215 |
+
"step": 260
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 3.802816901408451,
|
219 |
+
"grad_norm": 1.002933382987976,
|
220 |
+
"learning_rate": 0.0001940532081377152,
|
221 |
+
"loss": 0.1657,
|
222 |
+
"step": 270
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 3.943661971830986,
|
226 |
+
"grad_norm": 0.6921798586845398,
|
227 |
+
"learning_rate": 0.0001930099113197705,
|
228 |
+
"loss": 0.1881,
|
229 |
+
"step": 280
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 4.084507042253521,
|
233 |
+
"grad_norm": 0.5872893333435059,
|
234 |
+
"learning_rate": 0.0001919666145018258,
|
235 |
+
"loss": 0.1775,
|
236 |
+
"step": 290
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 4.225352112676056,
|
240 |
+
"grad_norm": 0.7991660833358765,
|
241 |
+
"learning_rate": 0.0001909233176838811,
|
242 |
+
"loss": 0.1338,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 4.225352112676056,
|
247 |
+
"eval_accuracy": 0.9376760563380282,
|
248 |
+
"eval_f1": 0.8448729184925504,
|
249 |
+
"eval_loss": 0.1607813537120819,
|
250 |
+
"eval_precision": 0.8397212543554007,
|
251 |
+
"eval_recall": 0.8500881834215167,
|
252 |
+
"eval_runtime": 4.716,
|
253 |
+
"eval_samples_per_second": 60.22,
|
254 |
+
"eval_steps_per_second": 7.634,
|
255 |
+
"step": 300
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 4.366197183098592,
|
259 |
+
"grad_norm": 0.3925558030605316,
|
260 |
+
"learning_rate": 0.00018988002086593636,
|
261 |
+
"loss": 0.1397,
|
262 |
+
"step": 310
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 4.507042253521127,
|
266 |
+
"grad_norm": 0.9107651114463806,
|
267 |
+
"learning_rate": 0.00018883672404799165,
|
268 |
+
"loss": 0.1328,
|
269 |
+
"step": 320
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 4.647887323943662,
|
273 |
+
"grad_norm": 0.6482114791870117,
|
274 |
+
"learning_rate": 0.00018779342723004695,
|
275 |
+
"loss": 0.1343,
|
276 |
+
"step": 330
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 4.788732394366197,
|
280 |
+
"grad_norm": 0.8836609125137329,
|
281 |
+
"learning_rate": 0.00018675013041210225,
|
282 |
+
"loss": 0.1527,
|
283 |
+
"step": 340
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 4.929577464788732,
|
287 |
+
"grad_norm": 0.8424317240715027,
|
288 |
+
"learning_rate": 0.00018570683359415754,
|
289 |
+
"loss": 0.1338,
|
290 |
+
"step": 350
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 5.070422535211268,
|
294 |
+
"grad_norm": 0.824109673500061,
|
295 |
+
"learning_rate": 0.00018466353677621284,
|
296 |
+
"loss": 0.1455,
|
297 |
+
"step": 360
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 5.211267605633803,
|
301 |
+
"grad_norm": 0.7583167552947998,
|
302 |
+
"learning_rate": 0.00018362023995826813,
|
303 |
+
"loss": 0.1045,
|
304 |
+
"step": 370
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 5.352112676056338,
|
308 |
+
"grad_norm": 0.9834734797477722,
|
309 |
+
"learning_rate": 0.00018257694314032343,
|
310 |
+
"loss": 0.1297,
|
311 |
+
"step": 380
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 5.492957746478873,
|
315 |
+
"grad_norm": 0.6775982975959778,
|
316 |
+
"learning_rate": 0.00018153364632237873,
|
317 |
+
"loss": 0.1382,
|
318 |
+
"step": 390
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 5.633802816901408,
|
322 |
+
"grad_norm": 0.4346470236778259,
|
323 |
+
"learning_rate": 0.00018049034950443402,
|
324 |
+
"loss": 0.1224,
|
325 |
+
"step": 400
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 5.633802816901408,
|
329 |
+
"eval_accuracy": 0.9271126760563381,
|
330 |
+
"eval_f1": 0.8179419525065963,
|
331 |
+
"eval_loss": 0.17346476018428802,
|
332 |
+
"eval_precision": 0.8157894736842105,
|
333 |
+
"eval_recall": 0.8201058201058201,
|
334 |
+
"eval_runtime": 4.3151,
|
335 |
+
"eval_samples_per_second": 65.816,
|
336 |
+
"eval_steps_per_second": 8.343,
|
337 |
+
"step": 400
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 5.774647887323944,
|
341 |
+
"grad_norm": 0.6250389218330383,
|
342 |
+
"learning_rate": 0.00017944705268648932,
|
343 |
+
"loss": 0.1535,
|
344 |
+
"step": 410
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 5.915492957746479,
|
348 |
+
"grad_norm": 0.7581302523612976,
|
349 |
+
"learning_rate": 0.00017840375586854461,
|
350 |
+
"loss": 0.1217,
|
351 |
+
"step": 420
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 6.056338028169014,
|
355 |
+
"grad_norm": 1.0700663328170776,
|
356 |
+
"learning_rate": 0.0001773604590505999,
|
357 |
+
"loss": 0.1206,
|
358 |
+
"step": 430
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 6.197183098591549,
|
362 |
+
"grad_norm": 0.9656069278717041,
|
363 |
+
"learning_rate": 0.0001763171622326552,
|
364 |
+
"loss": 0.1063,
|
365 |
+
"step": 440
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 6.338028169014084,
|
369 |
+
"grad_norm": 0.8910039067268372,
|
370 |
+
"learning_rate": 0.0001752738654147105,
|
371 |
+
"loss": 0.1105,
|
372 |
+
"step": 450
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 6.47887323943662,
|
376 |
+
"grad_norm": 1.0498372316360474,
|
377 |
+
"learning_rate": 0.0001742305685967658,
|
378 |
+
"loss": 0.1064,
|
379 |
+
"step": 460
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 6.619718309859155,
|
383 |
+
"grad_norm": 0.8038674592971802,
|
384 |
+
"learning_rate": 0.00017318727177882107,
|
385 |
+
"loss": 0.1048,
|
386 |
+
"step": 470
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 6.76056338028169,
|
390 |
+
"grad_norm": 0.5430222749710083,
|
391 |
+
"learning_rate": 0.00017214397496087636,
|
392 |
+
"loss": 0.1081,
|
393 |
+
"step": 480
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 6.901408450704225,
|
397 |
+
"grad_norm": 0.6888221502304077,
|
398 |
+
"learning_rate": 0.00017110067814293166,
|
399 |
+
"loss": 0.1176,
|
400 |
+
"step": 490
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 7.042253521126761,
|
404 |
+
"grad_norm": 0.5913430452346802,
|
405 |
+
"learning_rate": 0.00017005738132498696,
|
406 |
+
"loss": 0.1065,
|
407 |
+
"step": 500
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 7.042253521126761,
|
411 |
+
"eval_accuracy": 0.9274647887323944,
|
412 |
+
"eval_f1": 0.8186619718309859,
|
413 |
+
"eval_loss": 0.18472303450107574,
|
414 |
+
"eval_precision": 0.8172231985940246,
|
415 |
+
"eval_recall": 0.8201058201058201,
|
416 |
+
"eval_runtime": 4.2833,
|
417 |
+
"eval_samples_per_second": 66.305,
|
418 |
+
"eval_steps_per_second": 8.405,
|
419 |
+
"step": 500
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 7.183098591549296,
|
423 |
+
"grad_norm": 0.7211888432502747,
|
424 |
+
"learning_rate": 0.00016901408450704225,
|
425 |
+
"loss": 0.0907,
|
426 |
+
"step": 510
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 7.323943661971831,
|
430 |
+
"grad_norm": 0.9712802767753601,
|
431 |
+
"learning_rate": 0.00016797078768909755,
|
432 |
+
"loss": 0.1174,
|
433 |
+
"step": 520
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 7.464788732394366,
|
437 |
+
"grad_norm": 0.5647371411323547,
|
438 |
+
"learning_rate": 0.00016692749087115284,
|
439 |
+
"loss": 0.1188,
|
440 |
+
"step": 530
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 7.605633802816901,
|
444 |
+
"grad_norm": 0.8738060593605042,
|
445 |
+
"learning_rate": 0.00016588419405320814,
|
446 |
+
"loss": 0.1261,
|
447 |
+
"step": 540
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 7.746478873239437,
|
451 |
+
"grad_norm": 0.4535655081272125,
|
452 |
+
"learning_rate": 0.00016484089723526344,
|
453 |
+
"loss": 0.0865,
|
454 |
+
"step": 550
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 7.887323943661972,
|
458 |
+
"grad_norm": 0.4072222411632538,
|
459 |
+
"learning_rate": 0.00016379760041731873,
|
460 |
+
"loss": 0.0974,
|
461 |
+
"step": 560
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 8.028169014084508,
|
465 |
+
"grad_norm": 0.36978864669799805,
|
466 |
+
"learning_rate": 0.00016275430359937403,
|
467 |
+
"loss": 0.0989,
|
468 |
+
"step": 570
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 8.169014084507042,
|
472 |
+
"grad_norm": 0.6507691740989685,
|
473 |
+
"learning_rate": 0.00016171100678142932,
|
474 |
+
"loss": 0.0989,
|
475 |
+
"step": 580
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 8.309859154929578,
|
479 |
+
"grad_norm": 0.8923565149307251,
|
480 |
+
"learning_rate": 0.00016066770996348462,
|
481 |
+
"loss": 0.0901,
|
482 |
+
"step": 590
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 8.450704225352112,
|
486 |
+
"grad_norm": 0.8466383814811707,
|
487 |
+
"learning_rate": 0.00015962441314553992,
|
488 |
+
"loss": 0.1008,
|
489 |
+
"step": 600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 8.450704225352112,
|
493 |
+
"eval_accuracy": 0.9404929577464789,
|
494 |
+
"eval_f1": 0.8505747126436781,
|
495 |
+
"eval_loss": 0.17097999155521393,
|
496 |
+
"eval_precision": 0.8528368794326241,
|
497 |
+
"eval_recall": 0.8483245149911817,
|
498 |
+
"eval_runtime": 3.9495,
|
499 |
+
"eval_samples_per_second": 71.908,
|
500 |
+
"eval_steps_per_second": 9.115,
|
501 |
+
"step": 600
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 8.591549295774648,
|
505 |
+
"grad_norm": 0.568720817565918,
|
506 |
+
"learning_rate": 0.0001585811163275952,
|
507 |
+
"loss": 0.084,
|
508 |
+
"step": 610
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 8.732394366197184,
|
512 |
+
"grad_norm": 0.6025291085243225,
|
513 |
+
"learning_rate": 0.0001575378195096505,
|
514 |
+
"loss": 0.1059,
|
515 |
+
"step": 620
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 8.873239436619718,
|
519 |
+
"grad_norm": 0.6547625660896301,
|
520 |
+
"learning_rate": 0.0001564945226917058,
|
521 |
+
"loss": 0.0871,
|
522 |
+
"step": 630
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 9.014084507042254,
|
526 |
+
"grad_norm": 0.46392133831977844,
|
527 |
+
"learning_rate": 0.00015545122587376107,
|
528 |
+
"loss": 0.0856,
|
529 |
+
"step": 640
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 9.154929577464788,
|
533 |
+
"grad_norm": 0.29296088218688965,
|
534 |
+
"learning_rate": 0.00015440792905581637,
|
535 |
+
"loss": 0.0883,
|
536 |
+
"step": 650
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 9.295774647887324,
|
540 |
+
"grad_norm": 0.6499446630477905,
|
541 |
+
"learning_rate": 0.00015336463223787167,
|
542 |
+
"loss": 0.0632,
|
543 |
+
"step": 660
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 9.43661971830986,
|
547 |
+
"grad_norm": 0.27808037400245667,
|
548 |
+
"learning_rate": 0.00015232133541992696,
|
549 |
+
"loss": 0.0731,
|
550 |
+
"step": 670
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 9.577464788732394,
|
554 |
+
"grad_norm": 0.6585447788238525,
|
555 |
+
"learning_rate": 0.00015127803860198226,
|
556 |
+
"loss": 0.073,
|
557 |
+
"step": 680
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 9.71830985915493,
|
561 |
+
"grad_norm": 0.5550310611724854,
|
562 |
+
"learning_rate": 0.00015023474178403755,
|
563 |
+
"loss": 0.0762,
|
564 |
+
"step": 690
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 9.859154929577464,
|
568 |
+
"grad_norm": 0.8603278398513794,
|
569 |
+
"learning_rate": 0.00014919144496609285,
|
570 |
+
"loss": 0.1005,
|
571 |
+
"step": 700
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 9.859154929577464,
|
575 |
+
"eval_accuracy": 0.9383802816901409,
|
576 |
+
"eval_f1": 0.8404740200546946,
|
577 |
+
"eval_loss": 0.18234650790691376,
|
578 |
+
"eval_precision": 0.869811320754717,
|
579 |
+
"eval_recall": 0.8130511463844797,
|
580 |
+
"eval_runtime": 4.0053,
|
581 |
+
"eval_samples_per_second": 70.906,
|
582 |
+
"eval_steps_per_second": 8.988,
|
583 |
+
"step": 700
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 10.0,
|
587 |
+
"grad_norm": 0.5497912168502808,
|
588 |
+
"learning_rate": 0.00014814814814814815,
|
589 |
+
"loss": 0.0828,
|
590 |
+
"step": 710
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 10.140845070422536,
|
594 |
+
"grad_norm": 0.5562108755111694,
|
595 |
+
"learning_rate": 0.00014710485133020344,
|
596 |
+
"loss": 0.0771,
|
597 |
+
"step": 720
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 10.28169014084507,
|
601 |
+
"grad_norm": 0.5177081823348999,
|
602 |
+
"learning_rate": 0.00014606155451225874,
|
603 |
+
"loss": 0.0699,
|
604 |
+
"step": 730
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 10.422535211267606,
|
608 |
+
"grad_norm": 1.1959189176559448,
|
609 |
+
"learning_rate": 0.00014501825769431403,
|
610 |
+
"loss": 0.0706,
|
611 |
+
"step": 740
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 10.56338028169014,
|
615 |
+
"grad_norm": 0.41302013397216797,
|
616 |
+
"learning_rate": 0.00014397496087636933,
|
617 |
+
"loss": 0.0562,
|
618 |
+
"step": 750
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 10.704225352112676,
|
622 |
+
"grad_norm": 0.8963214159011841,
|
623 |
+
"learning_rate": 0.00014293166405842463,
|
624 |
+
"loss": 0.0795,
|
625 |
+
"step": 760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 10.845070422535212,
|
629 |
+
"grad_norm": 0.5553390979766846,
|
630 |
+
"learning_rate": 0.00014188836724047992,
|
631 |
+
"loss": 0.0841,
|
632 |
+
"step": 770
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 10.985915492957746,
|
636 |
+
"grad_norm": 0.5120792984962463,
|
637 |
+
"learning_rate": 0.00014084507042253522,
|
638 |
+
"loss": 0.0571,
|
639 |
+
"step": 780
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 11.126760563380282,
|
643 |
+
"grad_norm": 0.8299622535705566,
|
644 |
+
"learning_rate": 0.00013980177360459051,
|
645 |
+
"loss": 0.0674,
|
646 |
+
"step": 790
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 11.267605633802816,
|
650 |
+
"grad_norm": 0.8283889889717102,
|
651 |
+
"learning_rate": 0.00013875847678664578,
|
652 |
+
"loss": 0.0756,
|
653 |
+
"step": 800
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 11.267605633802816,
|
657 |
+
"eval_accuracy": 0.9415492957746479,
|
658 |
+
"eval_f1": 0.8520499108734403,
|
659 |
+
"eval_loss": 0.1770765483379364,
|
660 |
+
"eval_precision": 0.8612612612612612,
|
661 |
+
"eval_recall": 0.8430335097001763,
|
662 |
+
"eval_runtime": 3.9753,
|
663 |
+
"eval_samples_per_second": 71.441,
|
664 |
+
"eval_steps_per_second": 9.056,
|
665 |
+
"step": 800
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 11.408450704225352,
|
669 |
+
"grad_norm": 0.7964696288108826,
|
670 |
+
"learning_rate": 0.00013771517996870108,
|
671 |
+
"loss": 0.0674,
|
672 |
+
"step": 810
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 11.549295774647888,
|
676 |
+
"grad_norm": 0.5819689631462097,
|
677 |
+
"learning_rate": 0.00013667188315075638,
|
678 |
+
"loss": 0.0744,
|
679 |
+
"step": 820
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 11.690140845070422,
|
683 |
+
"grad_norm": 0.4807089865207672,
|
684 |
+
"learning_rate": 0.0001356285863328117,
|
685 |
+
"loss": 0.09,
|
686 |
+
"step": 830
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 11.830985915492958,
|
690 |
+
"grad_norm": 0.4166727364063263,
|
691 |
+
"learning_rate": 0.000134585289514867,
|
692 |
+
"loss": 0.057,
|
693 |
+
"step": 840
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 11.971830985915492,
|
697 |
+
"grad_norm": 0.5973660349845886,
|
698 |
+
"learning_rate": 0.0001335419926969223,
|
699 |
+
"loss": 0.0678,
|
700 |
+
"step": 850
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 12.112676056338028,
|
704 |
+
"grad_norm": 0.8271676898002625,
|
705 |
+
"learning_rate": 0.0001324986958789776,
|
706 |
+
"loss": 0.0676,
|
707 |
+
"step": 860
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 12.253521126760564,
|
711 |
+
"grad_norm": 0.4148211181163788,
|
712 |
+
"learning_rate": 0.00013145539906103288,
|
713 |
+
"loss": 0.0724,
|
714 |
+
"step": 870
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 12.394366197183098,
|
718 |
+
"grad_norm": 0.8119566440582275,
|
719 |
+
"learning_rate": 0.00013041210224308818,
|
720 |
+
"loss": 0.0513,
|
721 |
+
"step": 880
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 12.535211267605634,
|
725 |
+
"grad_norm": 0.3651484549045563,
|
726 |
+
"learning_rate": 0.00012936880542514348,
|
727 |
+
"loss": 0.0681,
|
728 |
+
"step": 890
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 12.676056338028168,
|
732 |
+
"grad_norm": 0.5199844241142273,
|
733 |
+
"learning_rate": 0.00012832550860719877,
|
734 |
+
"loss": 0.0653,
|
735 |
+
"step": 900
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 12.676056338028168,
|
739 |
+
"eval_accuracy": 0.9323943661971831,
|
740 |
+
"eval_f1": 0.8309859154929577,
|
741 |
+
"eval_loss": 0.1971179097890854,
|
742 |
+
"eval_precision": 0.8295254833040422,
|
743 |
+
"eval_recall": 0.8324514991181657,
|
744 |
+
"eval_runtime": 4.0066,
|
745 |
+
"eval_samples_per_second": 70.884,
|
746 |
+
"eval_steps_per_second": 8.985,
|
747 |
+
"step": 900
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 12.816901408450704,
|
751 |
+
"grad_norm": 0.5670329332351685,
|
752 |
+
"learning_rate": 0.00012728221178925407,
|
753 |
+
"loss": 0.0619,
|
754 |
+
"step": 910
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 12.95774647887324,
|
758 |
+
"grad_norm": 0.5461100935935974,
|
759 |
+
"learning_rate": 0.00012623891497130936,
|
760 |
+
"loss": 0.0411,
|
761 |
+
"step": 920
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 13.098591549295774,
|
765 |
+
"grad_norm": 0.5733127593994141,
|
766 |
+
"learning_rate": 0.00012519561815336466,
|
767 |
+
"loss": 0.0544,
|
768 |
+
"step": 930
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 13.23943661971831,
|
772 |
+
"grad_norm": 1.001535177230835,
|
773 |
+
"learning_rate": 0.00012415232133541993,
|
774 |
+
"loss": 0.0723,
|
775 |
+
"step": 940
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 13.380281690140846,
|
779 |
+
"grad_norm": 0.4734277129173279,
|
780 |
+
"learning_rate": 0.00012310902451747523,
|
781 |
+
"loss": 0.0457,
|
782 |
+
"step": 950
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 13.52112676056338,
|
786 |
+
"grad_norm": 0.41569235920906067,
|
787 |
+
"learning_rate": 0.00012206572769953053,
|
788 |
+
"loss": 0.0611,
|
789 |
+
"step": 960
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 13.661971830985916,
|
793 |
+
"grad_norm": 0.656200110912323,
|
794 |
+
"learning_rate": 0.00012102243088158583,
|
795 |
+
"loss": 0.0578,
|
796 |
+
"step": 970
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 13.80281690140845,
|
800 |
+
"grad_norm": 0.4374938905239105,
|
801 |
+
"learning_rate": 0.00011997913406364111,
|
802 |
+
"loss": 0.0493,
|
803 |
+
"step": 980
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 13.943661971830986,
|
807 |
+
"grad_norm": 0.4476602077484131,
|
808 |
+
"learning_rate": 0.00011893583724569641,
|
809 |
+
"loss": 0.0645,
|
810 |
+
"step": 990
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 14.084507042253522,
|
814 |
+
"grad_norm": 0.4841475784778595,
|
815 |
+
"learning_rate": 0.0001178925404277517,
|
816 |
+
"loss": 0.0367,
|
817 |
+
"step": 1000
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 14.084507042253522,
|
821 |
+
"eval_accuracy": 0.9295774647887324,
|
822 |
+
"eval_f1": 0.8220640569395018,
|
823 |
+
"eval_loss": 0.2123415768146515,
|
824 |
+
"eval_precision": 0.829443447037702,
|
825 |
+
"eval_recall": 0.8148148148148148,
|
826 |
+
"eval_runtime": 3.9803,
|
827 |
+
"eval_samples_per_second": 71.351,
|
828 |
+
"eval_steps_per_second": 9.045,
|
829 |
+
"step": 1000
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 14.225352112676056,
|
833 |
+
"grad_norm": 0.36940839886665344,
|
834 |
+
"learning_rate": 0.000116849243609807,
|
835 |
+
"loss": 0.0583,
|
836 |
+
"step": 1010
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 14.366197183098592,
|
840 |
+
"grad_norm": 0.360748291015625,
|
841 |
+
"learning_rate": 0.0001158059467918623,
|
842 |
+
"loss": 0.0557,
|
843 |
+
"step": 1020
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 14.507042253521126,
|
847 |
+
"grad_norm": 0.5215537548065186,
|
848 |
+
"learning_rate": 0.0001147626499739176,
|
849 |
+
"loss": 0.0687,
|
850 |
+
"step": 1030
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 14.647887323943662,
|
854 |
+
"grad_norm": 0.504537045955658,
|
855 |
+
"learning_rate": 0.00011371935315597289,
|
856 |
+
"loss": 0.07,
|
857 |
+
"step": 1040
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 14.788732394366198,
|
861 |
+
"grad_norm": 0.6165650486946106,
|
862 |
+
"learning_rate": 0.00011267605633802819,
|
863 |
+
"loss": 0.0527,
|
864 |
+
"step": 1050
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 14.929577464788732,
|
868 |
+
"grad_norm": 0.4196755588054657,
|
869 |
+
"learning_rate": 0.00011163275952008347,
|
870 |
+
"loss": 0.039,
|
871 |
+
"step": 1060
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 15.070422535211268,
|
875 |
+
"grad_norm": 0.789492130279541,
|
876 |
+
"learning_rate": 0.00011058946270213876,
|
877 |
+
"loss": 0.0518,
|
878 |
+
"step": 1070
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 15.211267605633802,
|
882 |
+
"grad_norm": 0.3040258288383484,
|
883 |
+
"learning_rate": 0.00010954616588419406,
|
884 |
+
"loss": 0.0426,
|
885 |
+
"step": 1080
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 15.352112676056338,
|
889 |
+
"grad_norm": 0.5353887677192688,
|
890 |
+
"learning_rate": 0.00010850286906624936,
|
891 |
+
"loss": 0.06,
|
892 |
+
"step": 1090
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 15.492957746478874,
|
896 |
+
"grad_norm": 0.4748779833316803,
|
897 |
+
"learning_rate": 0.00010745957224830465,
|
898 |
+
"loss": 0.0459,
|
899 |
+
"step": 1100
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 15.492957746478874,
|
903 |
+
"eval_accuracy": 0.9334507042253521,
|
904 |
+
"eval_f1": 0.832,
|
905 |
+
"eval_loss": 0.20056356489658356,
|
906 |
+
"eval_precision": 0.8387096774193549,
|
907 |
+
"eval_recall": 0.8253968253968254,
|
908 |
+
"eval_runtime": 3.8873,
|
909 |
+
"eval_samples_per_second": 73.058,
|
910 |
+
"eval_steps_per_second": 9.261,
|
911 |
+
"step": 1100
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 15.633802816901408,
|
915 |
+
"grad_norm": 1.0769853591918945,
|
916 |
+
"learning_rate": 0.00010641627543035995,
|
917 |
+
"loss": 0.0564,
|
918 |
+
"step": 1110
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 15.774647887323944,
|
922 |
+
"grad_norm": 0.2092517763376236,
|
923 |
+
"learning_rate": 0.00010537297861241524,
|
924 |
+
"loss": 0.037,
|
925 |
+
"step": 1120
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 15.915492957746478,
|
929 |
+
"grad_norm": 0.4689568877220154,
|
930 |
+
"learning_rate": 0.00010432968179447054,
|
931 |
+
"loss": 0.0401,
|
932 |
+
"step": 1130
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 16.056338028169016,
|
936 |
+
"grad_norm": 0.2354661524295807,
|
937 |
+
"learning_rate": 0.00010328638497652582,
|
938 |
+
"loss": 0.0459,
|
939 |
+
"step": 1140
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 16.197183098591548,
|
943 |
+
"grad_norm": 0.11875198781490326,
|
944 |
+
"learning_rate": 0.00010224308815858112,
|
945 |
+
"loss": 0.0369,
|
946 |
+
"step": 1150
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 16.338028169014084,
|
950 |
+
"grad_norm": 0.5551555156707764,
|
951 |
+
"learning_rate": 0.00010119979134063642,
|
952 |
+
"loss": 0.034,
|
953 |
+
"step": 1160
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 16.47887323943662,
|
957 |
+
"grad_norm": 0.35518983006477356,
|
958 |
+
"learning_rate": 0.00010015649452269171,
|
959 |
+
"loss": 0.0523,
|
960 |
+
"step": 1170
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 16.619718309859156,
|
964 |
+
"grad_norm": 0.6546155214309692,
|
965 |
+
"learning_rate": 9.911319770474701e-05,
|
966 |
+
"loss": 0.0472,
|
967 |
+
"step": 1180
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 16.760563380281692,
|
971 |
+
"grad_norm": 1.1401140689849854,
|
972 |
+
"learning_rate": 9.80699008868023e-05,
|
973 |
+
"loss": 0.0565,
|
974 |
+
"step": 1190
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 16.901408450704224,
|
978 |
+
"grad_norm": 0.5762555599212646,
|
979 |
+
"learning_rate": 9.70266040688576e-05,
|
980 |
+
"loss": 0.0559,
|
981 |
+
"step": 1200
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 16.901408450704224,
|
985 |
+
"eval_accuracy": 0.9313380281690141,
|
986 |
+
"eval_f1": 0.8232094288304623,
|
987 |
+
"eval_loss": 0.20966318249702454,
|
988 |
+
"eval_precision": 0.8470149253731343,
|
989 |
+
"eval_recall": 0.800705467372134,
|
990 |
+
"eval_runtime": 3.9873,
|
991 |
+
"eval_samples_per_second": 71.227,
|
992 |
+
"eval_steps_per_second": 9.029,
|
993 |
+
"step": 1200
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 17.04225352112676,
|
997 |
+
"grad_norm": 0.5705350637435913,
|
998 |
+
"learning_rate": 9.59833072509129e-05,
|
999 |
+
"loss": 0.0455,
|
1000 |
+
"step": 1210
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 17.183098591549296,
|
1004 |
+
"grad_norm": 0.08219115436077118,
|
1005 |
+
"learning_rate": 9.494001043296818e-05,
|
1006 |
+
"loss": 0.029,
|
1007 |
+
"step": 1220
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 17.323943661971832,
|
1011 |
+
"grad_norm": 0.41505807638168335,
|
1012 |
+
"learning_rate": 9.389671361502347e-05,
|
1013 |
+
"loss": 0.05,
|
1014 |
+
"step": 1230
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 17.464788732394368,
|
1018 |
+
"grad_norm": 0.5585283637046814,
|
1019 |
+
"learning_rate": 9.285341679707877e-05,
|
1020 |
+
"loss": 0.0424,
|
1021 |
+
"step": 1240
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 17.6056338028169,
|
1025 |
+
"grad_norm": 0.4773949980735779,
|
1026 |
+
"learning_rate": 9.181011997913407e-05,
|
1027 |
+
"loss": 0.043,
|
1028 |
+
"step": 1250
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 17.746478873239436,
|
1032 |
+
"grad_norm": 0.5886436700820923,
|
1033 |
+
"learning_rate": 9.076682316118936e-05,
|
1034 |
+
"loss": 0.043,
|
1035 |
+
"step": 1260
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 17.887323943661972,
|
1039 |
+
"grad_norm": 0.45917659997940063,
|
1040 |
+
"learning_rate": 8.972352634324466e-05,
|
1041 |
+
"loss": 0.0444,
|
1042 |
+
"step": 1270
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 18.028169014084508,
|
1046 |
+
"grad_norm": 0.5295466780662537,
|
1047 |
+
"learning_rate": 8.868022952529996e-05,
|
1048 |
+
"loss": 0.0385,
|
1049 |
+
"step": 1280
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 18.169014084507044,
|
1053 |
+
"grad_norm": 0.24455229938030243,
|
1054 |
+
"learning_rate": 8.763693270735525e-05,
|
1055 |
+
"loss": 0.0263,
|
1056 |
+
"step": 1290
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 18.309859154929576,
|
1060 |
+
"grad_norm": 0.34424206614494324,
|
1061 |
+
"learning_rate": 8.659363588941053e-05,
|
1062 |
+
"loss": 0.0382,
|
1063 |
+
"step": 1300
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 18.309859154929576,
|
1067 |
+
"eval_accuracy": 0.9352112676056338,
|
1068 |
+
"eval_f1": 0.8371681415929203,
|
1069 |
+
"eval_loss": 0.2055191993713379,
|
1070 |
+
"eval_precision": 0.8401420959147424,
|
1071 |
+
"eval_recall": 0.8342151675485009,
|
1072 |
+
"eval_runtime": 4.0365,
|
1073 |
+
"eval_samples_per_second": 70.358,
|
1074 |
+
"eval_steps_per_second": 8.919,
|
1075 |
+
"step": 1300
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 18.450704225352112,
|
1079 |
+
"grad_norm": 0.10903073102235794,
|
1080 |
+
"learning_rate": 8.555033907146583e-05,
|
1081 |
+
"loss": 0.0276,
|
1082 |
+
"step": 1310
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 18.591549295774648,
|
1086 |
+
"grad_norm": 0.4288780987262726,
|
1087 |
+
"learning_rate": 8.450704225352113e-05,
|
1088 |
+
"loss": 0.0457,
|
1089 |
+
"step": 1320
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 18.732394366197184,
|
1093 |
+
"grad_norm": 0.9041640758514404,
|
1094 |
+
"learning_rate": 8.346374543557642e-05,
|
1095 |
+
"loss": 0.0404,
|
1096 |
+
"step": 1330
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 18.87323943661972,
|
1100 |
+
"grad_norm": 0.3118440806865692,
|
1101 |
+
"learning_rate": 8.242044861763172e-05,
|
1102 |
+
"loss": 0.0404,
|
1103 |
+
"step": 1340
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 19.014084507042252,
|
1107 |
+
"grad_norm": 0.39209580421447754,
|
1108 |
+
"learning_rate": 8.137715179968701e-05,
|
1109 |
+
"loss": 0.029,
|
1110 |
+
"step": 1350
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 19.154929577464788,
|
1114 |
+
"grad_norm": 0.6325451731681824,
|
1115 |
+
"learning_rate": 8.033385498174231e-05,
|
1116 |
+
"loss": 0.0299,
|
1117 |
+
"step": 1360
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 19.295774647887324,
|
1121 |
+
"grad_norm": 0.33151936531066895,
|
1122 |
+
"learning_rate": 7.92905581637976e-05,
|
1123 |
+
"loss": 0.0277,
|
1124 |
+
"step": 1370
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 19.43661971830986,
|
1128 |
+
"grad_norm": 0.40647652745246887,
|
1129 |
+
"learning_rate": 7.82472613458529e-05,
|
1130 |
+
"loss": 0.0285,
|
1131 |
+
"step": 1380
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 19.577464788732396,
|
1135 |
+
"grad_norm": 0.3072868585586548,
|
1136 |
+
"learning_rate": 7.720396452790818e-05,
|
1137 |
+
"loss": 0.0314,
|
1138 |
+
"step": 1390
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 19.718309859154928,
|
1142 |
+
"grad_norm": 0.6823632121086121,
|
1143 |
+
"learning_rate": 7.616066770996348e-05,
|
1144 |
+
"loss": 0.0361,
|
1145 |
+
"step": 1400
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 19.718309859154928,
|
1149 |
+
"eval_accuracy": 0.9334507042253521,
|
1150 |
+
"eval_f1": 0.8304932735426009,
|
1151 |
+
"eval_loss": 0.20700237154960632,
|
1152 |
+
"eval_precision": 0.8448905109489051,
|
1153 |
+
"eval_recall": 0.8165784832451499,
|
1154 |
+
"eval_runtime": 4.3433,
|
1155 |
+
"eval_samples_per_second": 65.388,
|
1156 |
+
"eval_steps_per_second": 8.289,
|
1157 |
+
"step": 1400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 19.859154929577464,
|
1161 |
+
"grad_norm": 0.4812707006931305,
|
1162 |
+
"learning_rate": 7.511737089201878e-05,
|
1163 |
+
"loss": 0.0515,
|
1164 |
+
"step": 1410
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 20.0,
|
1168 |
+
"grad_norm": 0.9425677061080933,
|
1169 |
+
"learning_rate": 7.407407407407407e-05,
|
1170 |
+
"loss": 0.0408,
|
1171 |
+
"step": 1420
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 20.140845070422536,
|
1175 |
+
"grad_norm": 0.23266366124153137,
|
1176 |
+
"learning_rate": 7.303077725612937e-05,
|
1177 |
+
"loss": 0.033,
|
1178 |
+
"step": 1430
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 20.281690140845072,
|
1182 |
+
"grad_norm": 0.6943417191505432,
|
1183 |
+
"learning_rate": 7.198748043818467e-05,
|
1184 |
+
"loss": 0.0371,
|
1185 |
+
"step": 1440
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 20.422535211267604,
|
1189 |
+
"grad_norm": 0.5533664226531982,
|
1190 |
+
"learning_rate": 7.094418362023996e-05,
|
1191 |
+
"loss": 0.0333,
|
1192 |
+
"step": 1450
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 20.56338028169014,
|
1196 |
+
"grad_norm": 0.3414551913738251,
|
1197 |
+
"learning_rate": 6.990088680229526e-05,
|
1198 |
+
"loss": 0.0344,
|
1199 |
+
"step": 1460
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 20.704225352112676,
|
1203 |
+
"grad_norm": 0.21747425198554993,
|
1204 |
+
"learning_rate": 6.885758998435054e-05,
|
1205 |
+
"loss": 0.0507,
|
1206 |
+
"step": 1470
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 20.845070422535212,
|
1210 |
+
"grad_norm": 0.10106892138719559,
|
1211 |
+
"learning_rate": 6.781429316640585e-05,
|
1212 |
+
"loss": 0.0336,
|
1213 |
+
"step": 1480
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 20.985915492957748,
|
1217 |
+
"grad_norm": 0.11431819200515747,
|
1218 |
+
"learning_rate": 6.677099634846115e-05,
|
1219 |
+
"loss": 0.0349,
|
1220 |
+
"step": 1490
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 21.12676056338028,
|
1224 |
+
"grad_norm": 0.24515172839164734,
|
1225 |
+
"learning_rate": 6.572769953051644e-05,
|
1226 |
+
"loss": 0.0358,
|
1227 |
+
"step": 1500
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 21.12676056338028,
|
1231 |
+
"eval_accuracy": 0.9397887323943662,
|
1232 |
+
"eval_f1": 0.8458070333633905,
|
1233 |
+
"eval_loss": 0.1959269642829895,
|
1234 |
+
"eval_precision": 0.8653136531365314,
|
1235 |
+
"eval_recall": 0.8271604938271605,
|
1236 |
+
"eval_runtime": 4.6741,
|
1237 |
+
"eval_samples_per_second": 60.76,
|
1238 |
+
"eval_steps_per_second": 7.702,
|
1239 |
+
"step": 1500
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 21.267605633802816,
|
1243 |
+
"grad_norm": 0.1288166046142578,
|
1244 |
+
"learning_rate": 6.468440271257174e-05,
|
1245 |
+
"loss": 0.0319,
|
1246 |
+
"step": 1510
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 21.408450704225352,
|
1250 |
+
"grad_norm": 0.3846772611141205,
|
1251 |
+
"learning_rate": 6.364110589462703e-05,
|
1252 |
+
"loss": 0.0292,
|
1253 |
+
"step": 1520
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 21.549295774647888,
|
1257 |
+
"grad_norm": 0.8348280191421509,
|
1258 |
+
"learning_rate": 6.259780907668233e-05,
|
1259 |
+
"loss": 0.0408,
|
1260 |
+
"step": 1530
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 21.690140845070424,
|
1264 |
+
"grad_norm": 0.24261720478534698,
|
1265 |
+
"learning_rate": 6.155451225873761e-05,
|
1266 |
+
"loss": 0.0279,
|
1267 |
+
"step": 1540
|
1268 |
+
},
|
1269 |
+
{
|
1270 |
+
"epoch": 21.830985915492956,
|
1271 |
+
"grad_norm": 0.5973533391952515,
|
1272 |
+
"learning_rate": 6.0511215440792915e-05,
|
1273 |
+
"loss": 0.0363,
|
1274 |
+
"step": 1550
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 21.971830985915492,
|
1278 |
+
"grad_norm": 0.3994261622428894,
|
1279 |
+
"learning_rate": 5.9467918622848205e-05,
|
1280 |
+
"loss": 0.0294,
|
1281 |
+
"step": 1560
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 22.112676056338028,
|
1285 |
+
"grad_norm": 0.2752346992492676,
|
1286 |
+
"learning_rate": 5.84246218049035e-05,
|
1287 |
+
"loss": 0.0355,
|
1288 |
+
"step": 1570
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 22.253521126760564,
|
1292 |
+
"grad_norm": 0.0635056421160698,
|
1293 |
+
"learning_rate": 5.73813249869588e-05,
|
1294 |
+
"loss": 0.0192,
|
1295 |
+
"step": 1580
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 22.3943661971831,
|
1299 |
+
"grad_norm": 0.4133341908454895,
|
1300 |
+
"learning_rate": 5.633802816901409e-05,
|
1301 |
+
"loss": 0.0412,
|
1302 |
+
"step": 1590
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 22.535211267605632,
|
1306 |
+
"grad_norm": 0.30646753311157227,
|
1307 |
+
"learning_rate": 5.529473135106938e-05,
|
1308 |
+
"loss": 0.0382,
|
1309 |
+
"step": 1600
|
1310 |
+
},
|
1311 |
+
{
|
1312 |
+
"epoch": 22.535211267605632,
|
1313 |
+
"eval_accuracy": 0.9320422535211268,
|
1314 |
+
"eval_f1": 0.8269058295964126,
|
1315 |
+
"eval_loss": 0.20972707867622375,
|
1316 |
+
"eval_precision": 0.8412408759124088,
|
1317 |
+
"eval_recall": 0.8130511463844797,
|
1318 |
+
"eval_runtime": 4.7317,
|
1319 |
+
"eval_samples_per_second": 60.021,
|
1320 |
+
"eval_steps_per_second": 7.608,
|
1321 |
+
"step": 1600
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 22.676056338028168,
|
1325 |
+
"grad_norm": 1.3331828117370605,
|
1326 |
+
"learning_rate": 5.425143453312468e-05,
|
1327 |
+
"loss": 0.0331,
|
1328 |
+
"step": 1610
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 22.816901408450704,
|
1332 |
+
"grad_norm": 0.5091800093650818,
|
1333 |
+
"learning_rate": 5.3208137715179974e-05,
|
1334 |
+
"loss": 0.0187,
|
1335 |
+
"step": 1620
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 22.95774647887324,
|
1339 |
+
"grad_norm": 0.1486244797706604,
|
1340 |
+
"learning_rate": 5.216484089723527e-05,
|
1341 |
+
"loss": 0.02,
|
1342 |
+
"step": 1630
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 23.098591549295776,
|
1346 |
+
"grad_norm": 0.07892175763845444,
|
1347 |
+
"learning_rate": 5.112154407929056e-05,
|
1348 |
+
"loss": 0.0254,
|
1349 |
+
"step": 1640
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 23.239436619718308,
|
1353 |
+
"grad_norm": 0.7007431387901306,
|
1354 |
+
"learning_rate": 5.0078247261345856e-05,
|
1355 |
+
"loss": 0.0179,
|
1356 |
+
"step": 1650
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 23.380281690140844,
|
1360 |
+
"grad_norm": 0.4025111496448517,
|
1361 |
+
"learning_rate": 4.903495044340115e-05,
|
1362 |
+
"loss": 0.0256,
|
1363 |
+
"step": 1660
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 23.52112676056338,
|
1367 |
+
"grad_norm": 0.30540022253990173,
|
1368 |
+
"learning_rate": 4.799165362545645e-05,
|
1369 |
+
"loss": 0.0254,
|
1370 |
+
"step": 1670
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 23.661971830985916,
|
1374 |
+
"grad_norm": 0.45088985562324524,
|
1375 |
+
"learning_rate": 4.694835680751174e-05,
|
1376 |
+
"loss": 0.0326,
|
1377 |
+
"step": 1680
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 23.802816901408452,
|
1381 |
+
"grad_norm": 0.15087296068668365,
|
1382 |
+
"learning_rate": 4.5905059989567033e-05,
|
1383 |
+
"loss": 0.0229,
|
1384 |
+
"step": 1690
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 23.943661971830984,
|
1388 |
+
"grad_norm": 0.419587641954422,
|
1389 |
+
"learning_rate": 4.486176317162233e-05,
|
1390 |
+
"loss": 0.0285,
|
1391 |
+
"step": 1700
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 23.943661971830984,
|
1395 |
+
"eval_accuracy": 0.9415492957746479,
|
1396 |
+
"eval_f1": 0.851520572450805,
|
1397 |
+
"eval_loss": 0.20160087943077087,
|
1398 |
+
"eval_precision": 0.8638838475499092,
|
1399 |
+
"eval_recall": 0.8395061728395061,
|
1400 |
+
"eval_runtime": 4.681,
|
1401 |
+
"eval_samples_per_second": 60.671,
|
1402 |
+
"eval_steps_per_second": 7.691,
|
1403 |
+
"step": 1700
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 24.08450704225352,
|
1407 |
+
"grad_norm": 0.2833576202392578,
|
1408 |
+
"learning_rate": 4.3818466353677626e-05,
|
1409 |
+
"loss": 0.0136,
|
1410 |
+
"step": 1710
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 24.225352112676056,
|
1414 |
+
"grad_norm": 0.13959386944770813,
|
1415 |
+
"learning_rate": 4.2775169535732915e-05,
|
1416 |
+
"loss": 0.0195,
|
1417 |
+
"step": 1720
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 24.366197183098592,
|
1421 |
+
"grad_norm": 0.27296531200408936,
|
1422 |
+
"learning_rate": 4.173187271778821e-05,
|
1423 |
+
"loss": 0.0283,
|
1424 |
+
"step": 1730
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 24.507042253521128,
|
1428 |
+
"grad_norm": 0.21670201420783997,
|
1429 |
+
"learning_rate": 4.068857589984351e-05,
|
1430 |
+
"loss": 0.0196,
|
1431 |
+
"step": 1740
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 24.647887323943664,
|
1435 |
+
"grad_norm": 0.5724736452102661,
|
1436 |
+
"learning_rate": 3.96452790818988e-05,
|
1437 |
+
"loss": 0.031,
|
1438 |
+
"step": 1750
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 24.788732394366196,
|
1442 |
+
"grad_norm": 0.5493142604827881,
|
1443 |
+
"learning_rate": 3.860198226395409e-05,
|
1444 |
+
"loss": 0.0265,
|
1445 |
+
"step": 1760
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 24.929577464788732,
|
1449 |
+
"grad_norm": 0.21168898046016693,
|
1450 |
+
"learning_rate": 3.755868544600939e-05,
|
1451 |
+
"loss": 0.0224,
|
1452 |
+
"step": 1770
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 25.070422535211268,
|
1456 |
+
"grad_norm": 0.5312497019767761,
|
1457 |
+
"learning_rate": 3.6515388628064685e-05,
|
1458 |
+
"loss": 0.024,
|
1459 |
+
"step": 1780
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 25.211267605633804,
|
1463 |
+
"grad_norm": 0.5924656391143799,
|
1464 |
+
"learning_rate": 3.547209181011998e-05,
|
1465 |
+
"loss": 0.0151,
|
1466 |
+
"step": 1790
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 25.352112676056336,
|
1470 |
+
"grad_norm": 0.05471556633710861,
|
1471 |
+
"learning_rate": 3.442879499217527e-05,
|
1472 |
+
"loss": 0.0141,
|
1473 |
+
"step": 1800
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 25.352112676056336,
|
1477 |
+
"eval_accuracy": 0.9366197183098591,
|
1478 |
+
"eval_f1": 0.8384201077199281,
|
1479 |
+
"eval_loss": 0.2161274552345276,
|
1480 |
+
"eval_precision": 0.8537477148080439,
|
1481 |
+
"eval_recall": 0.8236331569664903,
|
1482 |
+
"eval_runtime": 4.5245,
|
1483 |
+
"eval_samples_per_second": 62.77,
|
1484 |
+
"eval_steps_per_second": 7.957,
|
1485 |
+
"step": 1800
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 25.492957746478872,
|
1489 |
+
"grad_norm": 0.2500435709953308,
|
1490 |
+
"learning_rate": 3.338549817423057e-05,
|
1491 |
+
"loss": 0.0177,
|
1492 |
+
"step": 1810
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 25.633802816901408,
|
1496 |
+
"grad_norm": 0.2633652985095978,
|
1497 |
+
"learning_rate": 3.234220135628587e-05,
|
1498 |
+
"loss": 0.0372,
|
1499 |
+
"step": 1820
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 25.774647887323944,
|
1503 |
+
"grad_norm": 0.2851497232913971,
|
1504 |
+
"learning_rate": 3.1298904538341165e-05,
|
1505 |
+
"loss": 0.0253,
|
1506 |
+
"step": 1830
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 25.91549295774648,
|
1510 |
+
"grad_norm": 0.13328520953655243,
|
1511 |
+
"learning_rate": 3.0255607720396458e-05,
|
1512 |
+
"loss": 0.0311,
|
1513 |
+
"step": 1840
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 26.056338028169016,
|
1517 |
+
"grad_norm": 0.5192949771881104,
|
1518 |
+
"learning_rate": 2.921231090245175e-05,
|
1519 |
+
"loss": 0.0155,
|
1520 |
+
"step": 1850
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 26.197183098591548,
|
1524 |
+
"grad_norm": 0.16768410801887512,
|
1525 |
+
"learning_rate": 2.8169014084507046e-05,
|
1526 |
+
"loss": 0.0282,
|
1527 |
+
"step": 1860
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 26.338028169014084,
|
1531 |
+
"grad_norm": 0.045551054179668427,
|
1532 |
+
"learning_rate": 2.712571726656234e-05,
|
1533 |
+
"loss": 0.0194,
|
1534 |
+
"step": 1870
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 26.47887323943662,
|
1538 |
+
"grad_norm": 0.33393070101737976,
|
1539 |
+
"learning_rate": 2.6082420448617635e-05,
|
1540 |
+
"loss": 0.0139,
|
1541 |
+
"step": 1880
|
1542 |
+
},
|
1543 |
+
{
|
1544 |
+
"epoch": 26.619718309859156,
|
1545 |
+
"grad_norm": 0.2400021106004715,
|
1546 |
+
"learning_rate": 2.5039123630672928e-05,
|
1547 |
+
"loss": 0.0111,
|
1548 |
+
"step": 1890
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 26.760563380281692,
|
1552 |
+
"grad_norm": 0.5022717118263245,
|
1553 |
+
"learning_rate": 2.3995826812728224e-05,
|
1554 |
+
"loss": 0.0179,
|
1555 |
+
"step": 1900
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 26.760563380281692,
|
1559 |
+
"eval_accuracy": 0.9376760563380282,
|
1560 |
+
"eval_f1": 0.8426666666666667,
|
1561 |
+
"eval_loss": 0.2072737216949463,
|
1562 |
+
"eval_precision": 0.8494623655913979,
|
1563 |
+
"eval_recall": 0.8359788359788359,
|
1564 |
+
"eval_runtime": 4.0574,
|
1565 |
+
"eval_samples_per_second": 69.995,
|
1566 |
+
"eval_steps_per_second": 8.873,
|
1567 |
+
"step": 1900
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"epoch": 26.901408450704224,
|
1571 |
+
"grad_norm": 0.41647252440452576,
|
1572 |
+
"learning_rate": 2.2952529994783517e-05,
|
1573 |
+
"loss": 0.0285,
|
1574 |
+
"step": 1910
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 27.04225352112676,
|
1578 |
+
"grad_norm": 0.3066710829734802,
|
1579 |
+
"learning_rate": 2.1909233176838813e-05,
|
1580 |
+
"loss": 0.0225,
|
1581 |
+
"step": 1920
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 27.183098591549296,
|
1585 |
+
"grad_norm": 0.09687885642051697,
|
1586 |
+
"learning_rate": 2.0865936358894105e-05,
|
1587 |
+
"loss": 0.0109,
|
1588 |
+
"step": 1930
|
1589 |
+
},
|
1590 |
+
{
|
1591 |
+
"epoch": 27.323943661971832,
|
1592 |
+
"grad_norm": 0.25405797362327576,
|
1593 |
+
"learning_rate": 1.98226395409494e-05,
|
1594 |
+
"loss": 0.0204,
|
1595 |
+
"step": 1940
|
1596 |
+
},
|
1597 |
+
{
|
1598 |
+
"epoch": 27.464788732394368,
|
1599 |
+
"grad_norm": 0.06933202594518661,
|
1600 |
+
"learning_rate": 1.8779342723004694e-05,
|
1601 |
+
"loss": 0.0274,
|
1602 |
+
"step": 1950
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 27.6056338028169,
|
1606 |
+
"grad_norm": 0.13852407038211823,
|
1607 |
+
"learning_rate": 1.773604590505999e-05,
|
1608 |
+
"loss": 0.0194,
|
1609 |
+
"step": 1960
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 27.746478873239436,
|
1613 |
+
"grad_norm": 0.1922004669904709,
|
1614 |
+
"learning_rate": 1.6692749087115286e-05,
|
1615 |
+
"loss": 0.0228,
|
1616 |
+
"step": 1970
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 27.887323943661972,
|
1620 |
+
"grad_norm": 0.2851165235042572,
|
1621 |
+
"learning_rate": 1.5649452269170582e-05,
|
1622 |
+
"loss": 0.022,
|
1623 |
+
"step": 1980
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 28.028169014084508,
|
1627 |
+
"grad_norm": 0.30591297149658203,
|
1628 |
+
"learning_rate": 1.4606155451225875e-05,
|
1629 |
+
"loss": 0.0179,
|
1630 |
+
"step": 1990
|
1631 |
+
},
|
1632 |
+
{
|
1633 |
+
"epoch": 28.169014084507044,
|
1634 |
+
"grad_norm": 0.9221152067184448,
|
1635 |
+
"learning_rate": 1.356285863328117e-05,
|
1636 |
+
"loss": 0.0263,
|
1637 |
+
"step": 2000
|
1638 |
+
},
|
1639 |
+
{
|
1640 |
+
"epoch": 28.169014084507044,
|
1641 |
+
"eval_accuracy": 0.9390845070422535,
|
1642 |
+
"eval_f1": 0.8456735057983943,
|
1643 |
+
"eval_loss": 0.20973354578018188,
|
1644 |
+
"eval_precision": 0.855595667870036,
|
1645 |
+
"eval_recall": 0.8359788359788359,
|
1646 |
+
"eval_runtime": 3.8982,
|
1647 |
+
"eval_samples_per_second": 72.853,
|
1648 |
+
"eval_steps_per_second": 9.235,
|
1649 |
+
"step": 2000
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 28.309859154929576,
|
1653 |
+
"grad_norm": 0.2080974280834198,
|
1654 |
+
"learning_rate": 1.2519561815336464e-05,
|
1655 |
+
"loss": 0.0223,
|
1656 |
+
"step": 2010
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 28.450704225352112,
|
1660 |
+
"grad_norm": 0.265176385641098,
|
1661 |
+
"learning_rate": 1.1476264997391758e-05,
|
1662 |
+
"loss": 0.0156,
|
1663 |
+
"step": 2020
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 28.591549295774648,
|
1667 |
+
"grad_norm": 0.6490623950958252,
|
1668 |
+
"learning_rate": 1.0432968179447053e-05,
|
1669 |
+
"loss": 0.0143,
|
1670 |
+
"step": 2030
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 28.732394366197184,
|
1674 |
+
"grad_norm": 0.08013524860143661,
|
1675 |
+
"learning_rate": 9.389671361502347e-06,
|
1676 |
+
"loss": 0.0175,
|
1677 |
+
"step": 2040
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 28.87323943661972,
|
1681 |
+
"grad_norm": 0.24310840666294098,
|
1682 |
+
"learning_rate": 8.346374543557643e-06,
|
1683 |
+
"loss": 0.0208,
|
1684 |
+
"step": 2050
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 29.014084507042252,
|
1688 |
+
"grad_norm": 0.21826568245887756,
|
1689 |
+
"learning_rate": 7.303077725612938e-06,
|
1690 |
+
"loss": 0.0209,
|
1691 |
+
"step": 2060
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 29.154929577464788,
|
1695 |
+
"grad_norm": 0.10844382643699646,
|
1696 |
+
"learning_rate": 6.259780907668232e-06,
|
1697 |
+
"loss": 0.0122,
|
1698 |
+
"step": 2070
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 29.295774647887324,
|
1702 |
+
"grad_norm": 0.1837497502565384,
|
1703 |
+
"learning_rate": 5.216484089723526e-06,
|
1704 |
+
"loss": 0.0155,
|
1705 |
+
"step": 2080
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 29.43661971830986,
|
1709 |
+
"grad_norm": 0.8813931941986084,
|
1710 |
+
"learning_rate": 4.173187271778822e-06,
|
1711 |
+
"loss": 0.0229,
|
1712 |
+
"step": 2090
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 29.577464788732396,
|
1716 |
+
"grad_norm": 0.10835859924554825,
|
1717 |
+
"learning_rate": 3.129890453834116e-06,
|
1718 |
+
"loss": 0.0191,
|
1719 |
+
"step": 2100
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 29.577464788732396,
|
1723 |
+
"eval_accuracy": 0.9376760563380282,
|
1724 |
+
"eval_f1": 0.8415398388540735,
|
1725 |
+
"eval_loss": 0.21010643243789673,
|
1726 |
+
"eval_precision": 0.8545454545454545,
|
1727 |
+
"eval_recall": 0.8289241622574955,
|
1728 |
+
"eval_runtime": 4.0827,
|
1729 |
+
"eval_samples_per_second": 69.561,
|
1730 |
+
"eval_steps_per_second": 8.818,
|
1731 |
+
"step": 2100
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 29.718309859154928,
|
1735 |
+
"grad_norm": 0.5981993079185486,
|
1736 |
+
"learning_rate": 2.086593635889411e-06,
|
1737 |
+
"loss": 0.024,
|
1738 |
+
"step": 2110
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 29.859154929577464,
|
1742 |
+
"grad_norm": 0.029736319556832314,
|
1743 |
+
"learning_rate": 1.0432968179447054e-06,
|
1744 |
+
"loss": 0.0147,
|
1745 |
+
"step": 2120
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 30.0,
|
1749 |
+
"grad_norm": 0.1090225800871849,
|
1750 |
+
"learning_rate": 0.0,
|
1751 |
+
"loss": 0.0163,
|
1752 |
+
"step": 2130
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 30.0,
|
1756 |
+
"step": 2130,
|
1757 |
+
"total_flos": 7.774335248148726e+18,
|
1758 |
+
"train_loss": 0.08187752739294595,
|
1759 |
+
"train_runtime": 1287.2767,
|
1760 |
+
"train_samples_per_second": 26.428,
|
1761 |
+
"train_steps_per_second": 1.655
|
1762 |
+
}
|
1763 |
+
],
|
1764 |
+
"logging_steps": 10,
|
1765 |
+
"max_steps": 2130,
|
1766 |
+
"num_input_tokens_seen": 0,
|
1767 |
+
"num_train_epochs": 30,
|
1768 |
+
"save_steps": 500,
|
1769 |
+
"stateful_callbacks": {
|
1770 |
+
"TrainerControl": {
|
1771 |
+
"args": {
|
1772 |
+
"should_epoch_stop": false,
|
1773 |
+
"should_evaluate": false,
|
1774 |
+
"should_log": false,
|
1775 |
+
"should_save": true,
|
1776 |
+
"should_training_stop": true
|
1777 |
+
},
|
1778 |
+
"attributes": {}
|
1779 |
+
}
|
1780 |
+
},
|
1781 |
+
"total_flos": 7.774335248148726e+18,
|
1782 |
+
"train_batch_size": 16,
|
1783 |
+
"trial_name": null,
|
1784 |
+
"trial_params": null
|
1785 |
+
}
|