selmamalak
commited on
Commit
•
1f856a9
1
Parent(s):
88479c6
Model save
Browse files- README.md +5 -5
- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +1676 -0
README.md
CHANGED
@@ -23,11 +23,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
23 |
|
24 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the medmnist-v2 dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
-
- Loss: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
-
- Precision: 0.
|
29 |
-
- Recall: 0.
|
30 |
-
- F1: 0.
|
31 |
|
32 |
## Model description
|
33 |
|
|
|
23 |
|
24 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the medmnist-v2 dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
+
- Loss: 0.4609
|
27 |
+
- Accuracy: 0.8240
|
28 |
+
- Precision: 0.7895
|
29 |
+
- Recall: 0.7821
|
30 |
+
- F1: 0.7852
|
31 |
|
32 |
## Model description
|
33 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8239891267414203,
|
4 |
+
"eval_f1": 0.7852027158639473,
|
5 |
+
"eval_loss": 0.4609430432319641,
|
6 |
+
"eval_precision": 0.7894503286617733,
|
7 |
+
"eval_recall": 0.7820860597039324,
|
8 |
+
"eval_runtime": 74.5465,
|
9 |
+
"eval_samples_per_second": 118.436,
|
10 |
+
"eval_steps_per_second": 7.405,
|
11 |
+
"total_flos": 1.087396245164114e+19,
|
12 |
+
"train_loss": 0.7537981033325195,
|
13 |
+
"train_runtime": 2484.6922,
|
14 |
+
"train_samples_per_second": 56.104,
|
15 |
+
"train_steps_per_second": 0.877
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8239891267414203,
|
4 |
+
"eval_f1": 0.7852027158639473,
|
5 |
+
"eval_loss": 0.4609430432319641,
|
6 |
+
"eval_precision": 0.7894503286617733,
|
7 |
+
"eval_recall": 0.7820860597039324,
|
8 |
+
"eval_runtime": 74.5465,
|
9 |
+
"eval_samples_per_second": 118.436,
|
10 |
+
"eval_steps_per_second": 7.405
|
11 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 1.087396245164114e+19,
|
4 |
+
"train_loss": 0.7537981033325195,
|
5 |
+
"train_runtime": 2484.6922,
|
6 |
+
"train_samples_per_second": 56.104,
|
7 |
+
"train_steps_per_second": 0.877
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1676 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9049755301794453,
|
3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-lora-medmnistv2/checkpoint-2180",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2180,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05,
|
13 |
+
"grad_norm": 5.959507465362549,
|
14 |
+
"learning_rate": 0.004977064220183487,
|
15 |
+
"loss": 1.9585,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.09,
|
20 |
+
"grad_norm": 3.8976335525512695,
|
21 |
+
"learning_rate": 0.004954128440366973,
|
22 |
+
"loss": 1.3768,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.14,
|
27 |
+
"grad_norm": 2.9822118282318115,
|
28 |
+
"learning_rate": 0.004931192660550459,
|
29 |
+
"loss": 1.4236,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.18,
|
34 |
+
"grad_norm": 3.5010669231414795,
|
35 |
+
"learning_rate": 0.004908256880733945,
|
36 |
+
"loss": 1.2595,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.23,
|
41 |
+
"grad_norm": 4.538541793823242,
|
42 |
+
"learning_rate": 0.004887614678899083,
|
43 |
+
"loss": 1.4165,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.28,
|
48 |
+
"grad_norm": 3.172377586364746,
|
49 |
+
"learning_rate": 0.004864678899082569,
|
50 |
+
"loss": 1.1823,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.32,
|
55 |
+
"grad_norm": 2.388909101486206,
|
56 |
+
"learning_rate": 0.004841743119266055,
|
57 |
+
"loss": 1.1399,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.37,
|
62 |
+
"grad_norm": 2.9836621284484863,
|
63 |
+
"learning_rate": 0.004818807339449541,
|
64 |
+
"loss": 1.1484,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.41,
|
69 |
+
"grad_norm": 2.9791626930236816,
|
70 |
+
"learning_rate": 0.004795871559633028,
|
71 |
+
"loss": 1.1652,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.46,
|
76 |
+
"grad_norm": 2.8931291103363037,
|
77 |
+
"learning_rate": 0.004772935779816514,
|
78 |
+
"loss": 1.0614,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.5,
|
83 |
+
"grad_norm": 4.281805515289307,
|
84 |
+
"learning_rate": 0.00475,
|
85 |
+
"loss": 1.1816,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.55,
|
90 |
+
"grad_norm": 1.8973846435546875,
|
91 |
+
"learning_rate": 0.0047270642201834865,
|
92 |
+
"loss": 1.0441,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.6,
|
97 |
+
"grad_norm": 2.476250648498535,
|
98 |
+
"learning_rate": 0.004704128440366973,
|
99 |
+
"loss": 1.1724,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.64,
|
104 |
+
"grad_norm": 3.405545711517334,
|
105 |
+
"learning_rate": 0.004681192660550459,
|
106 |
+
"loss": 1.1089,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.69,
|
111 |
+
"grad_norm": 3.545285940170288,
|
112 |
+
"learning_rate": 0.0046582568807339445,
|
113 |
+
"loss": 0.9702,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.73,
|
118 |
+
"grad_norm": 2.000765085220337,
|
119 |
+
"learning_rate": 0.004635321100917431,
|
120 |
+
"loss": 1.0029,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.78,
|
125 |
+
"grad_norm": 3.3316946029663086,
|
126 |
+
"learning_rate": 0.004612385321100918,
|
127 |
+
"loss": 1.003,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.83,
|
132 |
+
"grad_norm": 2.2348740100860596,
|
133 |
+
"learning_rate": 0.004589449541284404,
|
134 |
+
"loss": 1.0428,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.87,
|
139 |
+
"grad_norm": 2.1600568294525146,
|
140 |
+
"learning_rate": 0.00456651376146789,
|
141 |
+
"loss": 1.0674,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.92,
|
146 |
+
"grad_norm": 3.6075286865234375,
|
147 |
+
"learning_rate": 0.0045435779816513765,
|
148 |
+
"loss": 1.0286,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.96,
|
153 |
+
"grad_norm": 1.731745719909668,
|
154 |
+
"learning_rate": 0.004520642201834862,
|
155 |
+
"loss": 0.9608,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.0,
|
160 |
+
"eval_accuracy": 0.7765089722675367,
|
161 |
+
"eval_f1": 0.7007285514340752,
|
162 |
+
"eval_loss": 0.6055155992507935,
|
163 |
+
"eval_precision": 0.7235333775207775,
|
164 |
+
"eval_recall": 0.7232886628310071,
|
165 |
+
"eval_runtime": 20.7254,
|
166 |
+
"eval_samples_per_second": 118.309,
|
167 |
+
"eval_steps_per_second": 7.43,
|
168 |
+
"step": 218
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 1.01,
|
172 |
+
"grad_norm": 2.186959981918335,
|
173 |
+
"learning_rate": 0.004497706422018349,
|
174 |
+
"loss": 1.0296,
|
175 |
+
"step": 220
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 1.06,
|
179 |
+
"grad_norm": 2.0718557834625244,
|
180 |
+
"learning_rate": 0.0044747706422018346,
|
181 |
+
"loss": 0.9602,
|
182 |
+
"step": 230
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.1,
|
186 |
+
"grad_norm": 2.098830461502075,
|
187 |
+
"learning_rate": 0.004451834862385321,
|
188 |
+
"loss": 0.9453,
|
189 |
+
"step": 240
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 1.15,
|
193 |
+
"grad_norm": 2.486630439758301,
|
194 |
+
"learning_rate": 0.004428899082568808,
|
195 |
+
"loss": 0.9209,
|
196 |
+
"step": 250
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 1.19,
|
200 |
+
"grad_norm": 2.0856552124023438,
|
201 |
+
"learning_rate": 0.0044059633027522934,
|
202 |
+
"loss": 1.0935,
|
203 |
+
"step": 260
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.24,
|
207 |
+
"grad_norm": 1.6093757152557373,
|
208 |
+
"learning_rate": 0.00438302752293578,
|
209 |
+
"loss": 1.0387,
|
210 |
+
"step": 270
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 1.28,
|
214 |
+
"grad_norm": 1.9845185279846191,
|
215 |
+
"learning_rate": 0.004360091743119266,
|
216 |
+
"loss": 0.9536,
|
217 |
+
"step": 280
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 1.33,
|
221 |
+
"grad_norm": 2.10725474357605,
|
222 |
+
"learning_rate": 0.004337155963302752,
|
223 |
+
"loss": 0.8167,
|
224 |
+
"step": 290
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.38,
|
228 |
+
"grad_norm": 2.1504321098327637,
|
229 |
+
"learning_rate": 0.004314220183486239,
|
230 |
+
"loss": 0.9638,
|
231 |
+
"step": 300
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.42,
|
235 |
+
"grad_norm": 1.8799842596054077,
|
236 |
+
"learning_rate": 0.004291284403669725,
|
237 |
+
"loss": 0.9503,
|
238 |
+
"step": 310
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 1.47,
|
242 |
+
"grad_norm": 2.466273069381714,
|
243 |
+
"learning_rate": 0.004268348623853211,
|
244 |
+
"loss": 0.9487,
|
245 |
+
"step": 320
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.51,
|
249 |
+
"grad_norm": 1.635208249092102,
|
250 |
+
"learning_rate": 0.004245412844036698,
|
251 |
+
"loss": 0.9618,
|
252 |
+
"step": 330
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 1.56,
|
256 |
+
"grad_norm": 1.8513455390930176,
|
257 |
+
"learning_rate": 0.0042224770642201835,
|
258 |
+
"loss": 0.9647,
|
259 |
+
"step": 340
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 1.61,
|
263 |
+
"grad_norm": 2.562163829803467,
|
264 |
+
"learning_rate": 0.004199541284403669,
|
265 |
+
"loss": 0.9159,
|
266 |
+
"step": 350
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.65,
|
270 |
+
"grad_norm": 3.5535786151885986,
|
271 |
+
"learning_rate": 0.004176605504587156,
|
272 |
+
"loss": 1.109,
|
273 |
+
"step": 360
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 1.7,
|
277 |
+
"grad_norm": 2.6485819816589355,
|
278 |
+
"learning_rate": 0.004153669724770642,
|
279 |
+
"loss": 1.0044,
|
280 |
+
"step": 370
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 1.74,
|
284 |
+
"grad_norm": 2.7095954418182373,
|
285 |
+
"learning_rate": 0.004130733944954129,
|
286 |
+
"loss": 0.9123,
|
287 |
+
"step": 380
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.79,
|
291 |
+
"grad_norm": 1.9968432188034058,
|
292 |
+
"learning_rate": 0.004107798165137615,
|
293 |
+
"loss": 0.9469,
|
294 |
+
"step": 390
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 1.83,
|
298 |
+
"grad_norm": 2.2975969314575195,
|
299 |
+
"learning_rate": 0.004084862385321101,
|
300 |
+
"loss": 0.9568,
|
301 |
+
"step": 400
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 1.88,
|
305 |
+
"grad_norm": 3.4922454357147217,
|
306 |
+
"learning_rate": 0.004061926605504587,
|
307 |
+
"loss": 0.9636,
|
308 |
+
"step": 410
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.93,
|
312 |
+
"grad_norm": 1.8210103511810303,
|
313 |
+
"learning_rate": 0.004038990825688074,
|
314 |
+
"loss": 0.9296,
|
315 |
+
"step": 420
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.97,
|
319 |
+
"grad_norm": 2.032224655151367,
|
320 |
+
"learning_rate": 0.004016055045871559,
|
321 |
+
"loss": 0.9984,
|
322 |
+
"step": 430
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 2.0,
|
326 |
+
"eval_accuracy": 0.8066884176182708,
|
327 |
+
"eval_f1": 0.7113876383080939,
|
328 |
+
"eval_loss": 0.4811672270298004,
|
329 |
+
"eval_precision": 0.7265273055775476,
|
330 |
+
"eval_recall": 0.7320681182395002,
|
331 |
+
"eval_runtime": 20.7162,
|
332 |
+
"eval_samples_per_second": 118.362,
|
333 |
+
"eval_steps_per_second": 7.434,
|
334 |
+
"step": 436
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 2.02,
|
338 |
+
"grad_norm": 1.7719513177871704,
|
339 |
+
"learning_rate": 0.003995412844036697,
|
340 |
+
"loss": 0.9865,
|
341 |
+
"step": 440
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 2.06,
|
345 |
+
"grad_norm": 2.115173578262329,
|
346 |
+
"learning_rate": 0.003972477064220183,
|
347 |
+
"loss": 0.9227,
|
348 |
+
"step": 450
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 2.11,
|
352 |
+
"grad_norm": 1.707400918006897,
|
353 |
+
"learning_rate": 0.00394954128440367,
|
354 |
+
"loss": 0.9195,
|
355 |
+
"step": 460
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 2.16,
|
359 |
+
"grad_norm": 2.7709805965423584,
|
360 |
+
"learning_rate": 0.0039266055045871565,
|
361 |
+
"loss": 0.8792,
|
362 |
+
"step": 470
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 2.2,
|
366 |
+
"grad_norm": 2.1106033325195312,
|
367 |
+
"learning_rate": 0.003903669724770642,
|
368 |
+
"loss": 0.9282,
|
369 |
+
"step": 480
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 2.25,
|
373 |
+
"grad_norm": 2.2281219959259033,
|
374 |
+
"learning_rate": 0.0038807339449541283,
|
375 |
+
"loss": 0.8242,
|
376 |
+
"step": 490
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 2.29,
|
380 |
+
"grad_norm": 1.9189764261245728,
|
381 |
+
"learning_rate": 0.003857798165137615,
|
382 |
+
"loss": 0.8428,
|
383 |
+
"step": 500
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 2.34,
|
387 |
+
"grad_norm": 2.04294753074646,
|
388 |
+
"learning_rate": 0.003834862385321101,
|
389 |
+
"loss": 0.8726,
|
390 |
+
"step": 510
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 2.39,
|
394 |
+
"grad_norm": 2.139575481414795,
|
395 |
+
"learning_rate": 0.003811926605504587,
|
396 |
+
"loss": 0.9184,
|
397 |
+
"step": 520
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 2.43,
|
401 |
+
"grad_norm": 2.527928113937378,
|
402 |
+
"learning_rate": 0.0037889908256880734,
|
403 |
+
"loss": 0.934,
|
404 |
+
"step": 530
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 2.48,
|
408 |
+
"grad_norm": 1.9021204710006714,
|
409 |
+
"learning_rate": 0.00376605504587156,
|
410 |
+
"loss": 0.9117,
|
411 |
+
"step": 540
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 2.52,
|
415 |
+
"grad_norm": 2.099567174911499,
|
416 |
+
"learning_rate": 0.003743119266055046,
|
417 |
+
"loss": 0.7403,
|
418 |
+
"step": 550
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 2.57,
|
422 |
+
"grad_norm": 1.6857088804244995,
|
423 |
+
"learning_rate": 0.003720183486238532,
|
424 |
+
"loss": 0.8173,
|
425 |
+
"step": 560
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 2.61,
|
429 |
+
"grad_norm": 2.216789960861206,
|
430 |
+
"learning_rate": 0.0036972477064220184,
|
431 |
+
"loss": 0.9077,
|
432 |
+
"step": 570
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 2.66,
|
436 |
+
"grad_norm": 1.2876479625701904,
|
437 |
+
"learning_rate": 0.0036743119266055045,
|
438 |
+
"loss": 0.8218,
|
439 |
+
"step": 580
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 2.71,
|
443 |
+
"grad_norm": 1.7834821939468384,
|
444 |
+
"learning_rate": 0.003651376146788991,
|
445 |
+
"loss": 0.8954,
|
446 |
+
"step": 590
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 2.75,
|
450 |
+
"grad_norm": 2.3635175228118896,
|
451 |
+
"learning_rate": 0.003628440366972477,
|
452 |
+
"loss": 0.8818,
|
453 |
+
"step": 600
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 2.8,
|
457 |
+
"grad_norm": 1.9978779554367065,
|
458 |
+
"learning_rate": 0.0036055045871559634,
|
459 |
+
"loss": 0.9062,
|
460 |
+
"step": 610
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 2.84,
|
464 |
+
"grad_norm": 2.9038476943969727,
|
465 |
+
"learning_rate": 0.0035825688073394496,
|
466 |
+
"loss": 0.8452,
|
467 |
+
"step": 620
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 2.89,
|
471 |
+
"grad_norm": 1.843595027923584,
|
472 |
+
"learning_rate": 0.003559633027522936,
|
473 |
+
"loss": 0.8291,
|
474 |
+
"step": 630
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 2.94,
|
478 |
+
"grad_norm": 2.618366241455078,
|
479 |
+
"learning_rate": 0.003536697247706422,
|
480 |
+
"loss": 0.8661,
|
481 |
+
"step": 640
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 2.98,
|
485 |
+
"grad_norm": 1.8442063331604004,
|
486 |
+
"learning_rate": 0.003513761467889908,
|
487 |
+
"loss": 0.8265,
|
488 |
+
"step": 650
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 3.0,
|
492 |
+
"eval_accuracy": 0.851957585644372,
|
493 |
+
"eval_f1": 0.768301171782241,
|
494 |
+
"eval_loss": 0.3725639581680298,
|
495 |
+
"eval_precision": 0.800477076178721,
|
496 |
+
"eval_recall": 0.771278337679668,
|
497 |
+
"eval_runtime": 20.7103,
|
498 |
+
"eval_samples_per_second": 118.395,
|
499 |
+
"eval_steps_per_second": 7.436,
|
500 |
+
"step": 654
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 3.03,
|
504 |
+
"grad_norm": 2.050394058227539,
|
505 |
+
"learning_rate": 0.0034908256880733946,
|
506 |
+
"loss": 0.7888,
|
507 |
+
"step": 660
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 3.07,
|
511 |
+
"grad_norm": 2.184720993041992,
|
512 |
+
"learning_rate": 0.003467889908256881,
|
513 |
+
"loss": 0.8631,
|
514 |
+
"step": 670
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 3.12,
|
518 |
+
"grad_norm": 1.606249213218689,
|
519 |
+
"learning_rate": 0.003444954128440367,
|
520 |
+
"loss": 0.7822,
|
521 |
+
"step": 680
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 3.17,
|
525 |
+
"grad_norm": 2.3371753692626953,
|
526 |
+
"learning_rate": 0.003422018348623853,
|
527 |
+
"loss": 0.7497,
|
528 |
+
"step": 690
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 3.21,
|
532 |
+
"grad_norm": 2.1213464736938477,
|
533 |
+
"learning_rate": 0.0033990825688073397,
|
534 |
+
"loss": 0.8359,
|
535 |
+
"step": 700
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 3.26,
|
539 |
+
"grad_norm": 2.4342410564422607,
|
540 |
+
"learning_rate": 0.003376146788990826,
|
541 |
+
"loss": 0.8393,
|
542 |
+
"step": 710
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 3.3,
|
546 |
+
"grad_norm": 2.252201557159424,
|
547 |
+
"learning_rate": 0.003353211009174312,
|
548 |
+
"loss": 0.771,
|
549 |
+
"step": 720
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 3.35,
|
553 |
+
"grad_norm": 2.0991744995117188,
|
554 |
+
"learning_rate": 0.003330275229357798,
|
555 |
+
"loss": 0.8322,
|
556 |
+
"step": 730
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 3.39,
|
560 |
+
"grad_norm": 1.4995887279510498,
|
561 |
+
"learning_rate": 0.0033073394495412847,
|
562 |
+
"loss": 0.8652,
|
563 |
+
"step": 740
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 3.44,
|
567 |
+
"grad_norm": 1.8054556846618652,
|
568 |
+
"learning_rate": 0.003284403669724771,
|
569 |
+
"loss": 0.8594,
|
570 |
+
"step": 750
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 3.49,
|
574 |
+
"grad_norm": 1.846091389656067,
|
575 |
+
"learning_rate": 0.0032614678899082566,
|
576 |
+
"loss": 0.8507,
|
577 |
+
"step": 760
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 3.53,
|
581 |
+
"grad_norm": 2.486276149749756,
|
582 |
+
"learning_rate": 0.003238532110091743,
|
583 |
+
"loss": 0.8608,
|
584 |
+
"step": 770
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 3.58,
|
588 |
+
"grad_norm": 1.9299883842468262,
|
589 |
+
"learning_rate": 0.0032155963302752293,
|
590 |
+
"loss": 0.7887,
|
591 |
+
"step": 780
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 3.62,
|
595 |
+
"grad_norm": 1.7495784759521484,
|
596 |
+
"learning_rate": 0.003192660550458716,
|
597 |
+
"loss": 0.8364,
|
598 |
+
"step": 790
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 3.67,
|
602 |
+
"grad_norm": 1.4023948907852173,
|
603 |
+
"learning_rate": 0.0031697247706422016,
|
604 |
+
"loss": 0.8239,
|
605 |
+
"step": 800
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 3.72,
|
609 |
+
"grad_norm": 2.4405996799468994,
|
610 |
+
"learning_rate": 0.003146788990825688,
|
611 |
+
"loss": 0.7324,
|
612 |
+
"step": 810
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 3.76,
|
616 |
+
"grad_norm": 2.8213984966278076,
|
617 |
+
"learning_rate": 0.0031238532110091743,
|
618 |
+
"loss": 0.8305,
|
619 |
+
"step": 820
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 3.81,
|
623 |
+
"grad_norm": 1.9884538650512695,
|
624 |
+
"learning_rate": 0.003100917431192661,
|
625 |
+
"loss": 0.823,
|
626 |
+
"step": 830
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 3.85,
|
630 |
+
"grad_norm": 1.3576688766479492,
|
631 |
+
"learning_rate": 0.0030779816513761466,
|
632 |
+
"loss": 0.7203,
|
633 |
+
"step": 840
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 3.9,
|
637 |
+
"grad_norm": 1.8440253734588623,
|
638 |
+
"learning_rate": 0.0030550458715596328,
|
639 |
+
"loss": 0.7564,
|
640 |
+
"step": 850
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 3.94,
|
644 |
+
"grad_norm": 1.383427381515503,
|
645 |
+
"learning_rate": 0.0030321100917431194,
|
646 |
+
"loss": 0.7679,
|
647 |
+
"step": 860
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 3.99,
|
651 |
+
"grad_norm": 2.3057126998901367,
|
652 |
+
"learning_rate": 0.003009174311926606,
|
653 |
+
"loss": 0.7938,
|
654 |
+
"step": 870
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 4.0,
|
658 |
+
"eval_accuracy": 0.8507340946166395,
|
659 |
+
"eval_f1": 0.7554407269192587,
|
660 |
+
"eval_loss": 0.39133650064468384,
|
661 |
+
"eval_precision": 0.7811773459124496,
|
662 |
+
"eval_recall": 0.7830608562256607,
|
663 |
+
"eval_runtime": 20.8094,
|
664 |
+
"eval_samples_per_second": 117.831,
|
665 |
+
"eval_steps_per_second": 7.4,
|
666 |
+
"step": 872
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 4.04,
|
670 |
+
"grad_norm": 1.3315050601959229,
|
671 |
+
"learning_rate": 0.0029862385321100917,
|
672 |
+
"loss": 0.7701,
|
673 |
+
"step": 880
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 4.08,
|
677 |
+
"grad_norm": 2.4050934314727783,
|
678 |
+
"learning_rate": 0.002963302752293578,
|
679 |
+
"loss": 0.7967,
|
680 |
+
"step": 890
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 4.13,
|
684 |
+
"grad_norm": 1.3627427816390991,
|
685 |
+
"learning_rate": 0.0029403669724770644,
|
686 |
+
"loss": 0.8184,
|
687 |
+
"step": 900
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 4.17,
|
691 |
+
"grad_norm": 2.152087688446045,
|
692 |
+
"learning_rate": 0.0029174311926605506,
|
693 |
+
"loss": 0.7987,
|
694 |
+
"step": 910
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 4.22,
|
698 |
+
"grad_norm": 2.42413067817688,
|
699 |
+
"learning_rate": 0.0028944954128440367,
|
700 |
+
"loss": 0.7772,
|
701 |
+
"step": 920
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 4.27,
|
705 |
+
"grad_norm": 1.8017699718475342,
|
706 |
+
"learning_rate": 0.002871559633027523,
|
707 |
+
"loss": 0.7587,
|
708 |
+
"step": 930
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 4.31,
|
712 |
+
"grad_norm": 1.805237889289856,
|
713 |
+
"learning_rate": 0.0028486238532110094,
|
714 |
+
"loss": 0.7326,
|
715 |
+
"step": 940
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 4.36,
|
719 |
+
"grad_norm": 2.2268106937408447,
|
720 |
+
"learning_rate": 0.0028256880733944956,
|
721 |
+
"loss": 0.7293,
|
722 |
+
"step": 950
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 4.4,
|
726 |
+
"grad_norm": 2.386366605758667,
|
727 |
+
"learning_rate": 0.0028027522935779813,
|
728 |
+
"loss": 0.7396,
|
729 |
+
"step": 960
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 4.45,
|
733 |
+
"grad_norm": 2.0315840244293213,
|
734 |
+
"learning_rate": 0.002779816513761468,
|
735 |
+
"loss": 0.7131,
|
736 |
+
"step": 970
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 4.5,
|
740 |
+
"grad_norm": 2.1899399757385254,
|
741 |
+
"learning_rate": 0.002756880733944954,
|
742 |
+
"loss": 0.8073,
|
743 |
+
"step": 980
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 4.54,
|
747 |
+
"grad_norm": 1.614035725593567,
|
748 |
+
"learning_rate": 0.0027339449541284406,
|
749 |
+
"loss": 0.7168,
|
750 |
+
"step": 990
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 4.59,
|
754 |
+
"grad_norm": 2.4006643295288086,
|
755 |
+
"learning_rate": 0.0027110091743119263,
|
756 |
+
"loss": 0.7774,
|
757 |
+
"step": 1000
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 4.63,
|
761 |
+
"grad_norm": 2.3257529735565186,
|
762 |
+
"learning_rate": 0.002688073394495413,
|
763 |
+
"loss": 0.7808,
|
764 |
+
"step": 1010
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 4.68,
|
768 |
+
"grad_norm": 1.6664689779281616,
|
769 |
+
"learning_rate": 0.002665137614678899,
|
770 |
+
"loss": 0.717,
|
771 |
+
"step": 1020
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 4.72,
|
775 |
+
"grad_norm": 1.7779196500778198,
|
776 |
+
"learning_rate": 0.0026422018348623857,
|
777 |
+
"loss": 0.7697,
|
778 |
+
"step": 1030
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 4.77,
|
782 |
+
"grad_norm": 1.8458689451217651,
|
783 |
+
"learning_rate": 0.0026192660550458714,
|
784 |
+
"loss": 0.7384,
|
785 |
+
"step": 1040
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 4.82,
|
789 |
+
"grad_norm": 1.5530970096588135,
|
790 |
+
"learning_rate": 0.0025963302752293575,
|
791 |
+
"loss": 0.7411,
|
792 |
+
"step": 1050
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 4.86,
|
796 |
+
"grad_norm": 2.550743341445923,
|
797 |
+
"learning_rate": 0.002573394495412844,
|
798 |
+
"loss": 0.6985,
|
799 |
+
"step": 1060
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 4.91,
|
803 |
+
"grad_norm": 1.284894347190857,
|
804 |
+
"learning_rate": 0.0025504587155963303,
|
805 |
+
"loss": 0.7961,
|
806 |
+
"step": 1070
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 4.95,
|
810 |
+
"grad_norm": 1.5528652667999268,
|
811 |
+
"learning_rate": 0.0025275229357798164,
|
812 |
+
"loss": 0.8198,
|
813 |
+
"step": 1080
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 5.0,
|
817 |
+
"grad_norm": 2.2907180786132812,
|
818 |
+
"learning_rate": 0.0025045871559633026,
|
819 |
+
"loss": 0.8149,
|
820 |
+
"step": 1090
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 5.0,
|
824 |
+
"eval_accuracy": 0.8531810766721044,
|
825 |
+
"eval_f1": 0.7701622667658707,
|
826 |
+
"eval_loss": 0.3675837218761444,
|
827 |
+
"eval_precision": 0.7686624499292936,
|
828 |
+
"eval_recall": 0.8001667562361665,
|
829 |
+
"eval_runtime": 20.7465,
|
830 |
+
"eval_samples_per_second": 118.189,
|
831 |
+
"eval_steps_per_second": 7.423,
|
832 |
+
"step": 1090
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 5.05,
|
836 |
+
"grad_norm": 1.3846713304519653,
|
837 |
+
"learning_rate": 0.002481651376146789,
|
838 |
+
"loss": 0.6938,
|
839 |
+
"step": 1100
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 5.09,
|
843 |
+
"grad_norm": 1.6576237678527832,
|
844 |
+
"learning_rate": 0.0024587155963302753,
|
845 |
+
"loss": 0.7169,
|
846 |
+
"step": 1110
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 5.14,
|
850 |
+
"grad_norm": 1.8432438373565674,
|
851 |
+
"learning_rate": 0.0024357798165137614,
|
852 |
+
"loss": 0.7242,
|
853 |
+
"step": 1120
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 5.18,
|
857 |
+
"grad_norm": 1.9799226522445679,
|
858 |
+
"learning_rate": 0.002412844036697248,
|
859 |
+
"loss": 0.6667,
|
860 |
+
"step": 1130
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 5.23,
|
864 |
+
"grad_norm": 1.92507004737854,
|
865 |
+
"learning_rate": 0.002389908256880734,
|
866 |
+
"loss": 0.6681,
|
867 |
+
"step": 1140
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 5.28,
|
871 |
+
"grad_norm": 1.4437962770462036,
|
872 |
+
"learning_rate": 0.0023669724770642203,
|
873 |
+
"loss": 0.6618,
|
874 |
+
"step": 1150
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 5.32,
|
878 |
+
"grad_norm": 1.565990924835205,
|
879 |
+
"learning_rate": 0.0023440366972477065,
|
880 |
+
"loss": 0.7162,
|
881 |
+
"step": 1160
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 5.37,
|
885 |
+
"grad_norm": 1.7609509229660034,
|
886 |
+
"learning_rate": 0.0023211009174311926,
|
887 |
+
"loss": 0.6953,
|
888 |
+
"step": 1170
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 5.41,
|
892 |
+
"grad_norm": 1.402076005935669,
|
893 |
+
"learning_rate": 0.002298165137614679,
|
894 |
+
"loss": 0.7114,
|
895 |
+
"step": 1180
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 5.46,
|
899 |
+
"grad_norm": 1.542944312095642,
|
900 |
+
"learning_rate": 0.0022752293577981654,
|
901 |
+
"loss": 0.7695,
|
902 |
+
"step": 1190
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 5.5,
|
906 |
+
"grad_norm": 1.3250664472579956,
|
907 |
+
"learning_rate": 0.0022522935779816515,
|
908 |
+
"loss": 0.6984,
|
909 |
+
"step": 1200
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 5.55,
|
913 |
+
"grad_norm": 1.790968894958496,
|
914 |
+
"learning_rate": 0.0022293577981651377,
|
915 |
+
"loss": 0.7457,
|
916 |
+
"step": 1210
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 5.6,
|
920 |
+
"grad_norm": 1.8708348274230957,
|
921 |
+
"learning_rate": 0.002206422018348624,
|
922 |
+
"loss": 0.6854,
|
923 |
+
"step": 1220
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 5.64,
|
927 |
+
"grad_norm": 1.3669894933700562,
|
928 |
+
"learning_rate": 0.0021834862385321104,
|
929 |
+
"loss": 0.7601,
|
930 |
+
"step": 1230
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 5.69,
|
934 |
+
"grad_norm": 1.6164820194244385,
|
935 |
+
"learning_rate": 0.0021605504587155966,
|
936 |
+
"loss": 0.7015,
|
937 |
+
"step": 1240
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 5.73,
|
941 |
+
"grad_norm": 2.5344796180725098,
|
942 |
+
"learning_rate": 0.0021376146788990827,
|
943 |
+
"loss": 0.6816,
|
944 |
+
"step": 1250
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 5.78,
|
948 |
+
"grad_norm": 1.8224860429763794,
|
949 |
+
"learning_rate": 0.002114678899082569,
|
950 |
+
"loss": 0.7091,
|
951 |
+
"step": 1260
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 5.83,
|
955 |
+
"grad_norm": 2.3349053859710693,
|
956 |
+
"learning_rate": 0.002091743119266055,
|
957 |
+
"loss": 0.69,
|
958 |
+
"step": 1270
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 5.87,
|
962 |
+
"grad_norm": 1.742497444152832,
|
963 |
+
"learning_rate": 0.002068807339449541,
|
964 |
+
"loss": 0.6835,
|
965 |
+
"step": 1280
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 5.92,
|
969 |
+
"grad_norm": 1.6536716222763062,
|
970 |
+
"learning_rate": 0.0020458715596330277,
|
971 |
+
"loss": 0.6827,
|
972 |
+
"step": 1290
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 5.96,
|
976 |
+
"grad_norm": 1.6461354494094849,
|
977 |
+
"learning_rate": 0.002022935779816514,
|
978 |
+
"loss": 0.6737,
|
979 |
+
"step": 1300
|
980 |
+
},
|
981 |
+
{
|
982 |
+
"epoch": 6.0,
|
983 |
+
"eval_accuracy": 0.8674551386623165,
|
984 |
+
"eval_f1": 0.7933729473887552,
|
985 |
+
"eval_loss": 0.3304790258407593,
|
986 |
+
"eval_precision": 0.8306122822846135,
|
987 |
+
"eval_recall": 0.8116698887283952,
|
988 |
+
"eval_runtime": 20.7895,
|
989 |
+
"eval_samples_per_second": 117.944,
|
990 |
+
"eval_steps_per_second": 7.408,
|
991 |
+
"step": 1308
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 6.01,
|
995 |
+
"grad_norm": 1.2140992879867554,
|
996 |
+
"learning_rate": 0.002,
|
997 |
+
"loss": 0.6921,
|
998 |
+
"step": 1310
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 6.06,
|
1002 |
+
"grad_norm": 2.1813745498657227,
|
1003 |
+
"learning_rate": 0.001977064220183486,
|
1004 |
+
"loss": 0.7078,
|
1005 |
+
"step": 1320
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 6.1,
|
1009 |
+
"grad_norm": 1.2994489669799805,
|
1010 |
+
"learning_rate": 0.0019541284403669728,
|
1011 |
+
"loss": 0.6949,
|
1012 |
+
"step": 1330
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 6.15,
|
1016 |
+
"grad_norm": 1.4426566362380981,
|
1017 |
+
"learning_rate": 0.0019311926605504587,
|
1018 |
+
"loss": 0.6685,
|
1019 |
+
"step": 1340
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 6.19,
|
1023 |
+
"grad_norm": 1.5542079210281372,
|
1024 |
+
"learning_rate": 0.001908256880733945,
|
1025 |
+
"loss": 0.6823,
|
1026 |
+
"step": 1350
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 6.24,
|
1030 |
+
"grad_norm": 1.5096594095230103,
|
1031 |
+
"learning_rate": 0.0018853211009174312,
|
1032 |
+
"loss": 0.6203,
|
1033 |
+
"step": 1360
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 6.28,
|
1037 |
+
"grad_norm": 2.132112979888916,
|
1038 |
+
"learning_rate": 0.0018623853211009176,
|
1039 |
+
"loss": 0.6942,
|
1040 |
+
"step": 1370
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 6.33,
|
1044 |
+
"grad_norm": 2.1632845401763916,
|
1045 |
+
"learning_rate": 0.0018394495412844037,
|
1046 |
+
"loss": 0.5899,
|
1047 |
+
"step": 1380
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 6.38,
|
1051 |
+
"grad_norm": 1.6782176494598389,
|
1052 |
+
"learning_rate": 0.0018165137614678901,
|
1053 |
+
"loss": 0.6316,
|
1054 |
+
"step": 1390
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 6.42,
|
1058 |
+
"grad_norm": 1.1974135637283325,
|
1059 |
+
"learning_rate": 0.001793577981651376,
|
1060 |
+
"loss": 0.609,
|
1061 |
+
"step": 1400
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 6.47,
|
1065 |
+
"grad_norm": 1.8140075206756592,
|
1066 |
+
"learning_rate": 0.0017706422018348624,
|
1067 |
+
"loss": 0.65,
|
1068 |
+
"step": 1410
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 6.51,
|
1072 |
+
"grad_norm": 1.5135620832443237,
|
1073 |
+
"learning_rate": 0.0017477064220183486,
|
1074 |
+
"loss": 0.6201,
|
1075 |
+
"step": 1420
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 6.56,
|
1079 |
+
"grad_norm": 1.6838016510009766,
|
1080 |
+
"learning_rate": 0.001724770642201835,
|
1081 |
+
"loss": 0.6044,
|
1082 |
+
"step": 1430
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 6.61,
|
1086 |
+
"grad_norm": 1.55550217628479,
|
1087 |
+
"learning_rate": 0.001701834862385321,
|
1088 |
+
"loss": 0.6753,
|
1089 |
+
"step": 1440
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 6.65,
|
1093 |
+
"grad_norm": 1.8122529983520508,
|
1094 |
+
"learning_rate": 0.0016788990825688074,
|
1095 |
+
"loss": 0.6608,
|
1096 |
+
"step": 1450
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 6.7,
|
1100 |
+
"grad_norm": 2.207045555114746,
|
1101 |
+
"learning_rate": 0.0016559633027522936,
|
1102 |
+
"loss": 0.6132,
|
1103 |
+
"step": 1460
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 6.74,
|
1107 |
+
"grad_norm": 0.9892495274543762,
|
1108 |
+
"learning_rate": 0.00163302752293578,
|
1109 |
+
"loss": 0.6177,
|
1110 |
+
"step": 1470
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 6.79,
|
1114 |
+
"grad_norm": 2.4809529781341553,
|
1115 |
+
"learning_rate": 0.0016100917431192661,
|
1116 |
+
"loss": 0.5607,
|
1117 |
+
"step": 1480
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 6.83,
|
1121 |
+
"grad_norm": 1.430293083190918,
|
1122 |
+
"learning_rate": 0.0015871559633027525,
|
1123 |
+
"loss": 0.6822,
|
1124 |
+
"step": 1490
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 6.88,
|
1128 |
+
"grad_norm": 1.6523278951644897,
|
1129 |
+
"learning_rate": 0.0015642201834862384,
|
1130 |
+
"loss": 0.6486,
|
1131 |
+
"step": 1500
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 6.93,
|
1135 |
+
"grad_norm": 1.5746197700500488,
|
1136 |
+
"learning_rate": 0.0015412844036697248,
|
1137 |
+
"loss": 0.5902,
|
1138 |
+
"step": 1510
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 6.97,
|
1142 |
+
"grad_norm": 1.5833261013031006,
|
1143 |
+
"learning_rate": 0.001518348623853211,
|
1144 |
+
"loss": 0.5695,
|
1145 |
+
"step": 1520
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 7.0,
|
1149 |
+
"eval_accuracy": 0.9029363784665579,
|
1150 |
+
"eval_f1": 0.8321123007962286,
|
1151 |
+
"eval_loss": 0.24805299937725067,
|
1152 |
+
"eval_precision": 0.8545669814728453,
|
1153 |
+
"eval_recall": 0.8469225407396054,
|
1154 |
+
"eval_runtime": 20.7317,
|
1155 |
+
"eval_samples_per_second": 118.273,
|
1156 |
+
"eval_steps_per_second": 7.428,
|
1157 |
+
"step": 1526
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 7.02,
|
1161 |
+
"grad_norm": 1.8044548034667969,
|
1162 |
+
"learning_rate": 0.0014954128440366973,
|
1163 |
+
"loss": 0.5888,
|
1164 |
+
"step": 1530
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 7.06,
|
1168 |
+
"grad_norm": 1.9052773714065552,
|
1169 |
+
"learning_rate": 0.0014724770642201835,
|
1170 |
+
"loss": 0.5968,
|
1171 |
+
"step": 1540
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 7.11,
|
1175 |
+
"grad_norm": 1.835716962814331,
|
1176 |
+
"learning_rate": 0.0014495412844036698,
|
1177 |
+
"loss": 0.642,
|
1178 |
+
"step": 1550
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 7.16,
|
1182 |
+
"grad_norm": 1.3683079481124878,
|
1183 |
+
"learning_rate": 0.001426605504587156,
|
1184 |
+
"loss": 0.6627,
|
1185 |
+
"step": 1560
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 7.2,
|
1189 |
+
"grad_norm": 1.9506031274795532,
|
1190 |
+
"learning_rate": 0.0014036697247706423,
|
1191 |
+
"loss": 0.6054,
|
1192 |
+
"step": 1570
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 7.25,
|
1196 |
+
"grad_norm": 1.300554871559143,
|
1197 |
+
"learning_rate": 0.0013807339449541285,
|
1198 |
+
"loss": 0.6375,
|
1199 |
+
"step": 1580
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 7.29,
|
1203 |
+
"grad_norm": 2.0933167934417725,
|
1204 |
+
"learning_rate": 0.0013577981651376149,
|
1205 |
+
"loss": 0.5603,
|
1206 |
+
"step": 1590
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 7.34,
|
1210 |
+
"grad_norm": 1.0951093435287476,
|
1211 |
+
"learning_rate": 0.0013348623853211008,
|
1212 |
+
"loss": 0.5836,
|
1213 |
+
"step": 1600
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 7.39,
|
1217 |
+
"grad_norm": 1.186511516571045,
|
1218 |
+
"learning_rate": 0.0013119266055045872,
|
1219 |
+
"loss": 0.5877,
|
1220 |
+
"step": 1610
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 7.43,
|
1224 |
+
"grad_norm": 1.5988391637802124,
|
1225 |
+
"learning_rate": 0.0012889908256880733,
|
1226 |
+
"loss": 0.5868,
|
1227 |
+
"step": 1620
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 7.48,
|
1231 |
+
"grad_norm": 2.0407028198242188,
|
1232 |
+
"learning_rate": 0.0012660550458715597,
|
1233 |
+
"loss": 0.564,
|
1234 |
+
"step": 1630
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 7.52,
|
1238 |
+
"grad_norm": 1.4676613807678223,
|
1239 |
+
"learning_rate": 0.001243119266055046,
|
1240 |
+
"loss": 0.6205,
|
1241 |
+
"step": 1640
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 7.57,
|
1245 |
+
"grad_norm": 1.1794471740722656,
|
1246 |
+
"learning_rate": 0.0012201834862385322,
|
1247 |
+
"loss": 0.581,
|
1248 |
+
"step": 1650
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 7.61,
|
1252 |
+
"grad_norm": 1.7204222679138184,
|
1253 |
+
"learning_rate": 0.0011972477064220183,
|
1254 |
+
"loss": 0.6433,
|
1255 |
+
"step": 1660
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 7.66,
|
1259 |
+
"grad_norm": 1.7347933053970337,
|
1260 |
+
"learning_rate": 0.0011743119266055047,
|
1261 |
+
"loss": 0.6132,
|
1262 |
+
"step": 1670
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 7.71,
|
1266 |
+
"grad_norm": 1.0963069200515747,
|
1267 |
+
"learning_rate": 0.0011513761467889909,
|
1268 |
+
"loss": 0.5961,
|
1269 |
+
"step": 1680
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 7.75,
|
1273 |
+
"grad_norm": 1.0383723974227905,
|
1274 |
+
"learning_rate": 0.0011284403669724772,
|
1275 |
+
"loss": 0.5934,
|
1276 |
+
"step": 1690
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 7.8,
|
1280 |
+
"grad_norm": 1.314132809638977,
|
1281 |
+
"learning_rate": 0.0011055045871559634,
|
1282 |
+
"loss": 0.5667,
|
1283 |
+
"step": 1700
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 7.84,
|
1287 |
+
"grad_norm": 1.8448032140731812,
|
1288 |
+
"learning_rate": 0.0010825688073394495,
|
1289 |
+
"loss": 0.5999,
|
1290 |
+
"step": 1710
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 7.89,
|
1294 |
+
"grad_norm": 1.187971591949463,
|
1295 |
+
"learning_rate": 0.001059633027522936,
|
1296 |
+
"loss": 0.5668,
|
1297 |
+
"step": 1720
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 7.94,
|
1301 |
+
"grad_norm": 1.451027512550354,
|
1302 |
+
"learning_rate": 0.001036697247706422,
|
1303 |
+
"loss": 0.5928,
|
1304 |
+
"step": 1730
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 7.98,
|
1308 |
+
"grad_norm": 1.5274406671524048,
|
1309 |
+
"learning_rate": 0.0010137614678899084,
|
1310 |
+
"loss": 0.5857,
|
1311 |
+
"step": 1740
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 8.0,
|
1315 |
+
"eval_accuracy": 0.8923327895595432,
|
1316 |
+
"eval_f1": 0.8339907958679574,
|
1317 |
+
"eval_loss": 0.2911706566810608,
|
1318 |
+
"eval_precision": 0.8463533280759077,
|
1319 |
+
"eval_recall": 0.8356417778568457,
|
1320 |
+
"eval_runtime": 20.8398,
|
1321 |
+
"eval_samples_per_second": 117.66,
|
1322 |
+
"eval_steps_per_second": 7.39,
|
1323 |
+
"step": 1744
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 8.03,
|
1327 |
+
"grad_norm": 1.254504919052124,
|
1328 |
+
"learning_rate": 0.0009908256880733946,
|
1329 |
+
"loss": 0.5059,
|
1330 |
+
"step": 1750
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 8.07,
|
1334 |
+
"grad_norm": 1.3762636184692383,
|
1335 |
+
"learning_rate": 0.0009678899082568808,
|
1336 |
+
"loss": 0.578,
|
1337 |
+
"step": 1760
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 8.12,
|
1341 |
+
"grad_norm": 1.472004771232605,
|
1342 |
+
"learning_rate": 0.0009449541284403671,
|
1343 |
+
"loss": 0.5216,
|
1344 |
+
"step": 1770
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 8.17,
|
1348 |
+
"grad_norm": 1.5876396894454956,
|
1349 |
+
"learning_rate": 0.0009220183486238532,
|
1350 |
+
"loss": 0.5689,
|
1351 |
+
"step": 1780
|
1352 |
+
},
|
1353 |
+
{
|
1354 |
+
"epoch": 8.21,
|
1355 |
+
"grad_norm": 1.2409037351608276,
|
1356 |
+
"learning_rate": 0.0008990825688073395,
|
1357 |
+
"loss": 0.5571,
|
1358 |
+
"step": 1790
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 8.26,
|
1362 |
+
"grad_norm": 1.2082581520080566,
|
1363 |
+
"learning_rate": 0.0008761467889908258,
|
1364 |
+
"loss": 0.5809,
|
1365 |
+
"step": 1800
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 8.3,
|
1369 |
+
"grad_norm": 1.7171647548675537,
|
1370 |
+
"learning_rate": 0.000853211009174312,
|
1371 |
+
"loss": 0.5626,
|
1372 |
+
"step": 1810
|
1373 |
+
},
|
1374 |
+
{
|
1375 |
+
"epoch": 8.35,
|
1376 |
+
"grad_norm": 1.3834128379821777,
|
1377 |
+
"learning_rate": 0.0008302752293577983,
|
1378 |
+
"loss": 0.5362,
|
1379 |
+
"step": 1820
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 8.39,
|
1383 |
+
"grad_norm": 1.424574375152588,
|
1384 |
+
"learning_rate": 0.0008073394495412844,
|
1385 |
+
"loss": 0.5418,
|
1386 |
+
"step": 1830
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 8.44,
|
1390 |
+
"grad_norm": 1.5661699771881104,
|
1391 |
+
"learning_rate": 0.0007844036697247707,
|
1392 |
+
"loss": 0.5609,
|
1393 |
+
"step": 1840
|
1394 |
+
},
|
1395 |
+
{
|
1396 |
+
"epoch": 8.49,
|
1397 |
+
"grad_norm": 1.9551769495010376,
|
1398 |
+
"learning_rate": 0.0007614678899082569,
|
1399 |
+
"loss": 0.564,
|
1400 |
+
"step": 1850
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 8.53,
|
1404 |
+
"grad_norm": 1.084270715713501,
|
1405 |
+
"learning_rate": 0.0007385321100917432,
|
1406 |
+
"loss": 0.5121,
|
1407 |
+
"step": 1860
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 8.58,
|
1411 |
+
"grad_norm": 1.446973204612732,
|
1412 |
+
"learning_rate": 0.0007155963302752295,
|
1413 |
+
"loss": 0.569,
|
1414 |
+
"step": 1870
|
1415 |
+
},
|
1416 |
+
{
|
1417 |
+
"epoch": 8.62,
|
1418 |
+
"grad_norm": 1.3539941310882568,
|
1419 |
+
"learning_rate": 0.0006926605504587156,
|
1420 |
+
"loss": 0.525,
|
1421 |
+
"step": 1880
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 8.67,
|
1425 |
+
"grad_norm": 1.413223147392273,
|
1426 |
+
"learning_rate": 0.0006697247706422019,
|
1427 |
+
"loss": 0.4403,
|
1428 |
+
"step": 1890
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 8.72,
|
1432 |
+
"grad_norm": 1.3614115715026855,
|
1433 |
+
"learning_rate": 0.0006467889908256881,
|
1434 |
+
"loss": 0.553,
|
1435 |
+
"step": 1900
|
1436 |
+
},
|
1437 |
+
{
|
1438 |
+
"epoch": 8.76,
|
1439 |
+
"grad_norm": 1.2185453176498413,
|
1440 |
+
"learning_rate": 0.0006238532110091744,
|
1441 |
+
"loss": 0.5498,
|
1442 |
+
"step": 1910
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 8.81,
|
1446 |
+
"grad_norm": 1.3884397745132446,
|
1447 |
+
"learning_rate": 0.0006009174311926606,
|
1448 |
+
"loss": 0.5092,
|
1449 |
+
"step": 1920
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 8.85,
|
1453 |
+
"grad_norm": 1.2725589275360107,
|
1454 |
+
"learning_rate": 0.0005779816513761468,
|
1455 |
+
"loss": 0.5695,
|
1456 |
+
"step": 1930
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 8.9,
|
1460 |
+
"grad_norm": 1.2434947490692139,
|
1461 |
+
"learning_rate": 0.000555045871559633,
|
1462 |
+
"loss": 0.4998,
|
1463 |
+
"step": 1940
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 8.94,
|
1467 |
+
"grad_norm": 1.378146767616272,
|
1468 |
+
"learning_rate": 0.0005321100917431193,
|
1469 |
+
"loss": 0.5091,
|
1470 |
+
"step": 1950
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 8.99,
|
1474 |
+
"grad_norm": 1.3200100660324097,
|
1475 |
+
"learning_rate": 0.0005091743119266056,
|
1476 |
+
"loss": 0.4834,
|
1477 |
+
"step": 1960
|
1478 |
+
},
|
1479 |
+
{
|
1480 |
+
"epoch": 9.0,
|
1481 |
+
"eval_accuracy": 0.899673735725938,
|
1482 |
+
"eval_f1": 0.8285783762787183,
|
1483 |
+
"eval_loss": 0.2657569944858551,
|
1484 |
+
"eval_precision": 0.8428024691807685,
|
1485 |
+
"eval_recall": 0.8409794358062922,
|
1486 |
+
"eval_runtime": 20.7116,
|
1487 |
+
"eval_samples_per_second": 118.388,
|
1488 |
+
"eval_steps_per_second": 7.435,
|
1489 |
+
"step": 1962
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 9.04,
|
1493 |
+
"grad_norm": 1.1076021194458008,
|
1494 |
+
"learning_rate": 0.0004862385321100918,
|
1495 |
+
"loss": 0.5164,
|
1496 |
+
"step": 1970
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 9.08,
|
1500 |
+
"grad_norm": 1.50495445728302,
|
1501 |
+
"learning_rate": 0.00046330275229357804,
|
1502 |
+
"loss": 0.4388,
|
1503 |
+
"step": 1980
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 9.13,
|
1507 |
+
"grad_norm": 1.4007256031036377,
|
1508 |
+
"learning_rate": 0.00044036697247706424,
|
1509 |
+
"loss": 0.4761,
|
1510 |
+
"step": 1990
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 9.17,
|
1514 |
+
"grad_norm": 1.226333737373352,
|
1515 |
+
"learning_rate": 0.0004174311926605505,
|
1516 |
+
"loss": 0.4861,
|
1517 |
+
"step": 2000
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 9.22,
|
1521 |
+
"grad_norm": 1.937953233718872,
|
1522 |
+
"learning_rate": 0.0003944954128440367,
|
1523 |
+
"loss": 0.4604,
|
1524 |
+
"step": 2010
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 9.27,
|
1528 |
+
"grad_norm": 1.35695219039917,
|
1529 |
+
"learning_rate": 0.00037155963302752296,
|
1530 |
+
"loss": 0.4633,
|
1531 |
+
"step": 2020
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 9.31,
|
1535 |
+
"grad_norm": 1.521087884902954,
|
1536 |
+
"learning_rate": 0.0003486238532110092,
|
1537 |
+
"loss": 0.4512,
|
1538 |
+
"step": 2030
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 9.36,
|
1542 |
+
"grad_norm": 1.4338667392730713,
|
1543 |
+
"learning_rate": 0.0003256880733944954,
|
1544 |
+
"loss": 0.5439,
|
1545 |
+
"step": 2040
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 9.4,
|
1549 |
+
"grad_norm": 1.7897557020187378,
|
1550 |
+
"learning_rate": 0.0003027522935779817,
|
1551 |
+
"loss": 0.5278,
|
1552 |
+
"step": 2050
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 9.45,
|
1556 |
+
"grad_norm": 1.0933929681777954,
|
1557 |
+
"learning_rate": 0.0002798165137614679,
|
1558 |
+
"loss": 0.4592,
|
1559 |
+
"step": 2060
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 9.5,
|
1563 |
+
"grad_norm": 1.2754806280136108,
|
1564 |
+
"learning_rate": 0.00025688073394495415,
|
1565 |
+
"loss": 0.476,
|
1566 |
+
"step": 2070
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 9.54,
|
1570 |
+
"grad_norm": 1.724406361579895,
|
1571 |
+
"learning_rate": 0.00023394495412844038,
|
1572 |
+
"loss": 0.4963,
|
1573 |
+
"step": 2080
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 9.59,
|
1577 |
+
"grad_norm": 1.5604366064071655,
|
1578 |
+
"learning_rate": 0.0002110091743119266,
|
1579 |
+
"loss": 0.4926,
|
1580 |
+
"step": 2090
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 9.63,
|
1584 |
+
"grad_norm": 1.2408415079116821,
|
1585 |
+
"learning_rate": 0.00018807339449541287,
|
1586 |
+
"loss": 0.4954,
|
1587 |
+
"step": 2100
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 9.68,
|
1591 |
+
"grad_norm": 0.8950926065444946,
|
1592 |
+
"learning_rate": 0.0001651376146788991,
|
1593 |
+
"loss": 0.4444,
|
1594 |
+
"step": 2110
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 9.72,
|
1598 |
+
"grad_norm": 1.2199152708053589,
|
1599 |
+
"learning_rate": 0.00014220183486238534,
|
1600 |
+
"loss": 0.4606,
|
1601 |
+
"step": 2120
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 9.77,
|
1605 |
+
"grad_norm": 1.1516410112380981,
|
1606 |
+
"learning_rate": 0.00011926605504587157,
|
1607 |
+
"loss": 0.4691,
|
1608 |
+
"step": 2130
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 9.82,
|
1612 |
+
"grad_norm": 2.192310333251953,
|
1613 |
+
"learning_rate": 9.63302752293578e-05,
|
1614 |
+
"loss": 0.5306,
|
1615 |
+
"step": 2140
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 9.86,
|
1619 |
+
"grad_norm": 1.2649255990982056,
|
1620 |
+
"learning_rate": 7.339449541284404e-05,
|
1621 |
+
"loss": 0.5238,
|
1622 |
+
"step": 2150
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 9.91,
|
1626 |
+
"grad_norm": 1.5681147575378418,
|
1627 |
+
"learning_rate": 5.0458715596330276e-05,
|
1628 |
+
"loss": 0.4631,
|
1629 |
+
"step": 2160
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 9.95,
|
1633 |
+
"grad_norm": 1.3230477571487427,
|
1634 |
+
"learning_rate": 2.7522935779816515e-05,
|
1635 |
+
"loss": 0.4716,
|
1636 |
+
"step": 2170
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"epoch": 10.0,
|
1640 |
+
"grad_norm": 1.0949994325637817,
|
1641 |
+
"learning_rate": 4.587155963302753e-06,
|
1642 |
+
"loss": 0.5287,
|
1643 |
+
"step": 2180
|
1644 |
+
},
|
1645 |
+
{
|
1646 |
+
"epoch": 10.0,
|
1647 |
+
"eval_accuracy": 0.9049755301794453,
|
1648 |
+
"eval_f1": 0.8468363122524573,
|
1649 |
+
"eval_loss": 0.2590215504169464,
|
1650 |
+
"eval_precision": 0.8523921546408058,
|
1651 |
+
"eval_recall": 0.8468399455092634,
|
1652 |
+
"eval_runtime": 20.6801,
|
1653 |
+
"eval_samples_per_second": 118.568,
|
1654 |
+
"eval_steps_per_second": 7.447,
|
1655 |
+
"step": 2180
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 10.0,
|
1659 |
+
"step": 2180,
|
1660 |
+
"total_flos": 1.087396245164114e+19,
|
1661 |
+
"train_loss": 0.7537981033325195,
|
1662 |
+
"train_runtime": 2484.6922,
|
1663 |
+
"train_samples_per_second": 56.104,
|
1664 |
+
"train_steps_per_second": 0.877
|
1665 |
+
}
|
1666 |
+
],
|
1667 |
+
"logging_steps": 10,
|
1668 |
+
"max_steps": 2180,
|
1669 |
+
"num_input_tokens_seen": 0,
|
1670 |
+
"num_train_epochs": 10,
|
1671 |
+
"save_steps": 500,
|
1672 |
+
"total_flos": 1.087396245164114e+19,
|
1673 |
+
"train_batch_size": 16,
|
1674 |
+
"trial_name": null,
|
1675 |
+
"trial_params": null
|
1676 |
+
}
|