End of training
Browse files- README.md +9 -9
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Oct22_02-50-10_7bf328c0e77a/events.out.tfevents.1729566009.7bf328c0e77a.215.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1443 -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 [apple/mobilevitv2-1.0-imagenet1k-256](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256) 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: 0.9444444444444444
|
30 |
- name: F1
|
31 |
type: f1
|
32 |
+
value: 0.8544819557625145
|
33 |
- name: Precision
|
34 |
type: precision
|
35 |
+
value: 0.8615023474178404
|
36 |
- name: Recall
|
37 |
type: recall
|
38 |
+
value: 0.8475750577367206
|
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 [apple/mobilevitv2-1.0-imagenet1k-256](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256) on the webdataset dataset.
|
47 |
It achieves the following results on the evaluation set:
|
48 |
+
- Loss: 0.1539
|
49 |
+
- Accuracy: 0.9444
|
50 |
+
- F1: 0.8545
|
51 |
+
- Precision: 0.8615
|
52 |
+
- Recall: 0.8476
|
53 |
|
54 |
## Model description
|
55 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"eval_accuracy": 0.9444444444444444,
|
4 |
+
"eval_f1": 0.8544819557625145,
|
5 |
+
"eval_loss": 0.15389865636825562,
|
6 |
+
"eval_precision": 0.8615023474178404,
|
7 |
+
"eval_recall": 0.8475750577367206,
|
8 |
+
"eval_runtime": 2.2689,
|
9 |
+
"eval_samples_per_second": 99.169,
|
10 |
+
"eval_steps_per_second": 12.782,
|
11 |
+
"total_flos": 1.77124415883264e+17,
|
12 |
+
"train_loss": 0.20865077226482637,
|
13 |
+
"train_runtime": 373.9101,
|
14 |
+
"train_samples_per_second": 72.21,
|
15 |
+
"train_steps_per_second": 4.573
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"eval_accuracy": 0.9444444444444444,
|
4 |
+
"eval_f1": 0.8544819557625145,
|
5 |
+
"eval_loss": 0.15389865636825562,
|
6 |
+
"eval_precision": 0.8615023474178404,
|
7 |
+
"eval_recall": 0.8475750577367206,
|
8 |
+
"eval_runtime": 2.2689,
|
9 |
+
"eval_samples_per_second": 99.169,
|
10 |
+
"eval_steps_per_second": 12.782
|
11 |
+
}
|
runs/Oct22_02-50-10_7bf328c0e77a/events.out.tfevents.1729566009.7bf328c0e77a.215.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d4b8c7a57e2e385e416ecaeb7cf42ddab99ec5e21e881a69fe9bb3b12466e47
|
3 |
+
size 560
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 30.0,
|
3 |
+
"total_flos": 1.77124415883264e+17,
|
4 |
+
"train_loss": 0.20865077226482637,
|
5 |
+
"train_runtime": 373.9101,
|
6 |
+
"train_samples_per_second": 72.21,
|
7 |
+
"train_steps_per_second": 4.573
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.15389865636825562,
|
3 |
+
"best_model_checkpoint": "mobilevitv2-1.0-imagenet1k-256-finetuned_v2024-10-21-frost/checkpoint-1000",
|
4 |
+
"epoch": 30.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 1710,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.17543859649122806,
|
13 |
+
"grad_norm": 0.3124828040599823,
|
14 |
+
"learning_rate": 1.1695906432748537e-05,
|
15 |
+
"loss": 0.6955,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3508771929824561,
|
20 |
+
"grad_norm": 0.24917739629745483,
|
21 |
+
"learning_rate": 2.3391812865497074e-05,
|
22 |
+
"loss": 0.6942,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5263157894736842,
|
27 |
+
"grad_norm": 0.2268371284008026,
|
28 |
+
"learning_rate": 3.508771929824561e-05,
|
29 |
+
"loss": 0.6939,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.7017543859649122,
|
34 |
+
"grad_norm": 0.2435961812734604,
|
35 |
+
"learning_rate": 4.678362573099415e-05,
|
36 |
+
"loss": 0.6918,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.8771929824561403,
|
41 |
+
"grad_norm": 0.24638999998569489,
|
42 |
+
"learning_rate": 5.847953216374269e-05,
|
43 |
+
"loss": 0.6889,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0526315789473684,
|
48 |
+
"grad_norm": 0.2426590472459793,
|
49 |
+
"learning_rate": 7.017543859649122e-05,
|
50 |
+
"loss": 0.6854,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.2280701754385965,
|
55 |
+
"grad_norm": 0.26534757018089294,
|
56 |
+
"learning_rate": 8.187134502923976e-05,
|
57 |
+
"loss": 0.6803,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.4035087719298245,
|
62 |
+
"grad_norm": 0.2573549449443817,
|
63 |
+
"learning_rate": 9.35672514619883e-05,
|
64 |
+
"loss": 0.6763,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.5789473684210527,
|
69 |
+
"grad_norm": 0.2639031410217285,
|
70 |
+
"learning_rate": 0.00010526315789473685,
|
71 |
+
"loss": 0.6701,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.7543859649122808,
|
76 |
+
"grad_norm": 0.26114630699157715,
|
77 |
+
"learning_rate": 0.00011695906432748539,
|
78 |
+
"loss": 0.6635,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.7543859649122808,
|
83 |
+
"eval_accuracy": 0.7604444444444445,
|
84 |
+
"eval_f1": 0.5705179282868525,
|
85 |
+
"eval_loss": 0.6512863039970398,
|
86 |
+
"eval_precision": 0.43552311435523117,
|
87 |
+
"eval_recall": 0.8267898383371824,
|
88 |
+
"eval_runtime": 2.9095,
|
89 |
+
"eval_samples_per_second": 77.332,
|
90 |
+
"eval_steps_per_second": 9.967,
|
91 |
+
"step": 100
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.9298245614035088,
|
95 |
+
"grad_norm": 0.3371104896068573,
|
96 |
+
"learning_rate": 0.0001286549707602339,
|
97 |
+
"loss": 0.6502,
|
98 |
+
"step": 110
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.1052631578947367,
|
102 |
+
"grad_norm": 0.31244638562202454,
|
103 |
+
"learning_rate": 0.00014035087719298245,
|
104 |
+
"loss": 0.6343,
|
105 |
+
"step": 120
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.280701754385965,
|
109 |
+
"grad_norm": 0.47065746784210205,
|
110 |
+
"learning_rate": 0.00015204678362573098,
|
111 |
+
"loss": 0.6161,
|
112 |
+
"step": 130
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 2.456140350877193,
|
116 |
+
"grad_norm": 0.41640815138816833,
|
117 |
+
"learning_rate": 0.00016374269005847952,
|
118 |
+
"loss": 0.588,
|
119 |
+
"step": 140
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 2.6315789473684212,
|
123 |
+
"grad_norm": 0.34670090675354004,
|
124 |
+
"learning_rate": 0.00017543859649122806,
|
125 |
+
"loss": 0.5565,
|
126 |
+
"step": 150
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 2.807017543859649,
|
130 |
+
"grad_norm": 0.384328693151474,
|
131 |
+
"learning_rate": 0.0001871345029239766,
|
132 |
+
"loss": 0.5242,
|
133 |
+
"step": 160
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 2.982456140350877,
|
137 |
+
"grad_norm": 0.4133964478969574,
|
138 |
+
"learning_rate": 0.00019883040935672513,
|
139 |
+
"loss": 0.5158,
|
140 |
+
"step": 170
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 3.1578947368421053,
|
144 |
+
"grad_norm": 0.4693595767021179,
|
145 |
+
"learning_rate": 0.00019883040935672513,
|
146 |
+
"loss": 0.4658,
|
147 |
+
"step": 180
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 3.3333333333333335,
|
151 |
+
"grad_norm": 0.41811782121658325,
|
152 |
+
"learning_rate": 0.00019753086419753085,
|
153 |
+
"loss": 0.4297,
|
154 |
+
"step": 190
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 3.5087719298245617,
|
158 |
+
"grad_norm": 0.8540976643562317,
|
159 |
+
"learning_rate": 0.00019623131903833657,
|
160 |
+
"loss": 0.4461,
|
161 |
+
"step": 200
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 3.5087719298245617,
|
165 |
+
"eval_accuracy": 0.8768888888888889,
|
166 |
+
"eval_f1": 0.729227761485826,
|
167 |
+
"eval_loss": 0.3972250819206238,
|
168 |
+
"eval_precision": 0.6322033898305085,
|
169 |
+
"eval_recall": 0.8614318706697459,
|
170 |
+
"eval_runtime": 1.766,
|
171 |
+
"eval_samples_per_second": 127.406,
|
172 |
+
"eval_steps_per_second": 16.421,
|
173 |
+
"step": 200
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 3.6842105263157894,
|
177 |
+
"grad_norm": 0.8259305357933044,
|
178 |
+
"learning_rate": 0.0001949317738791423,
|
179 |
+
"loss": 0.3914,
|
180 |
+
"step": 210
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 3.8596491228070176,
|
184 |
+
"grad_norm": 0.8546284437179565,
|
185 |
+
"learning_rate": 0.00019363222871994802,
|
186 |
+
"loss": 0.384,
|
187 |
+
"step": 220
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 4.035087719298246,
|
191 |
+
"grad_norm": 0.3827027678489685,
|
192 |
+
"learning_rate": 0.00019233268356075374,
|
193 |
+
"loss": 0.3497,
|
194 |
+
"step": 230
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 4.2105263157894735,
|
198 |
+
"grad_norm": 0.6248043775558472,
|
199 |
+
"learning_rate": 0.00019103313840155946,
|
200 |
+
"loss": 0.3648,
|
201 |
+
"step": 240
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 4.385964912280702,
|
205 |
+
"grad_norm": 0.5684685111045837,
|
206 |
+
"learning_rate": 0.00018973359324236518,
|
207 |
+
"loss": 0.3112,
|
208 |
+
"step": 250
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 4.56140350877193,
|
212 |
+
"grad_norm": 0.5080260634422302,
|
213 |
+
"learning_rate": 0.0001884340480831709,
|
214 |
+
"loss": 0.3059,
|
215 |
+
"step": 260
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 4.7368421052631575,
|
219 |
+
"grad_norm": 0.5282370448112488,
|
220 |
+
"learning_rate": 0.0001871345029239766,
|
221 |
+
"loss": 0.2922,
|
222 |
+
"step": 270
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 4.912280701754386,
|
226 |
+
"grad_norm": 0.7253307104110718,
|
227 |
+
"learning_rate": 0.00018583495776478232,
|
228 |
+
"loss": 0.2909,
|
229 |
+
"step": 280
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 5.087719298245614,
|
233 |
+
"grad_norm": 0.7058104276657104,
|
234 |
+
"learning_rate": 0.00018453541260558804,
|
235 |
+
"loss": 0.2922,
|
236 |
+
"step": 290
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 5.2631578947368425,
|
240 |
+
"grad_norm": 1.1993378400802612,
|
241 |
+
"learning_rate": 0.00018323586744639376,
|
242 |
+
"loss": 0.2599,
|
243 |
+
"step": 300
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 5.2631578947368425,
|
247 |
+
"eval_accuracy": 0.9226666666666666,
|
248 |
+
"eval_f1": 0.804932735426009,
|
249 |
+
"eval_loss": 0.2404223531484604,
|
250 |
+
"eval_precision": 0.7821350762527233,
|
251 |
+
"eval_recall": 0.8290993071593533,
|
252 |
+
"eval_runtime": 2.7313,
|
253 |
+
"eval_samples_per_second": 82.378,
|
254 |
+
"eval_steps_per_second": 10.618,
|
255 |
+
"step": 300
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 5.43859649122807,
|
259 |
+
"grad_norm": 0.8134835362434387,
|
260 |
+
"learning_rate": 0.00018193632228719948,
|
261 |
+
"loss": 0.2645,
|
262 |
+
"step": 310
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 5.614035087719298,
|
266 |
+
"grad_norm": 0.7742730975151062,
|
267 |
+
"learning_rate": 0.0001806367771280052,
|
268 |
+
"loss": 0.2345,
|
269 |
+
"step": 320
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 5.7894736842105265,
|
273 |
+
"grad_norm": 0.5191880464553833,
|
274 |
+
"learning_rate": 0.00017933723196881092,
|
275 |
+
"loss": 0.2504,
|
276 |
+
"step": 330
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 5.964912280701754,
|
280 |
+
"grad_norm": 0.7682189345359802,
|
281 |
+
"learning_rate": 0.00017803768680961664,
|
282 |
+
"loss": 0.2654,
|
283 |
+
"step": 340
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 6.140350877192983,
|
287 |
+
"grad_norm": 0.7704707384109497,
|
288 |
+
"learning_rate": 0.00017673814165042236,
|
289 |
+
"loss": 0.2431,
|
290 |
+
"step": 350
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 6.315789473684211,
|
294 |
+
"grad_norm": 0.9333469867706299,
|
295 |
+
"learning_rate": 0.00017543859649122806,
|
296 |
+
"loss": 0.2382,
|
297 |
+
"step": 360
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 6.491228070175438,
|
301 |
+
"grad_norm": 0.8412513136863708,
|
302 |
+
"learning_rate": 0.00017413905133203378,
|
303 |
+
"loss": 0.2207,
|
304 |
+
"step": 370
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 6.666666666666667,
|
308 |
+
"grad_norm": 0.7568041086196899,
|
309 |
+
"learning_rate": 0.0001728395061728395,
|
310 |
+
"loss": 0.2271,
|
311 |
+
"step": 380
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 6.842105263157895,
|
315 |
+
"grad_norm": 0.689445436000824,
|
316 |
+
"learning_rate": 0.00017153996101364522,
|
317 |
+
"loss": 0.2076,
|
318 |
+
"step": 390
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 7.017543859649122,
|
322 |
+
"grad_norm": 0.7390238046646118,
|
323 |
+
"learning_rate": 0.00017024041585445094,
|
324 |
+
"loss": 0.2074,
|
325 |
+
"step": 400
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 7.017543859649122,
|
329 |
+
"eval_accuracy": 0.9346666666666666,
|
330 |
+
"eval_f1": 0.8256227758007118,
|
331 |
+
"eval_loss": 0.1941838562488556,
|
332 |
+
"eval_precision": 0.848780487804878,
|
333 |
+
"eval_recall": 0.8036951501154734,
|
334 |
+
"eval_runtime": 1.7733,
|
335 |
+
"eval_samples_per_second": 126.88,
|
336 |
+
"eval_steps_per_second": 16.353,
|
337 |
+
"step": 400
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 7.192982456140351,
|
341 |
+
"grad_norm": 0.4645775258541107,
|
342 |
+
"learning_rate": 0.00016894087069525666,
|
343 |
+
"loss": 0.2233,
|
344 |
+
"step": 410
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 7.368421052631579,
|
348 |
+
"grad_norm": 0.6826916337013245,
|
349 |
+
"learning_rate": 0.00016764132553606238,
|
350 |
+
"loss": 0.1846,
|
351 |
+
"step": 420
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 7.543859649122807,
|
355 |
+
"grad_norm": 0.6299170851707458,
|
356 |
+
"learning_rate": 0.0001663417803768681,
|
357 |
+
"loss": 0.1807,
|
358 |
+
"step": 430
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 7.719298245614035,
|
362 |
+
"grad_norm": 0.40688008069992065,
|
363 |
+
"learning_rate": 0.00016504223521767383,
|
364 |
+
"loss": 0.1925,
|
365 |
+
"step": 440
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 7.894736842105263,
|
369 |
+
"grad_norm": 0.8310642242431641,
|
370 |
+
"learning_rate": 0.00016374269005847952,
|
371 |
+
"loss": 0.1906,
|
372 |
+
"step": 450
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 8.070175438596491,
|
376 |
+
"grad_norm": 0.7561126351356506,
|
377 |
+
"learning_rate": 0.00016244314489928524,
|
378 |
+
"loss": 0.2537,
|
379 |
+
"step": 460
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 8.24561403508772,
|
383 |
+
"grad_norm": 1.5505608320236206,
|
384 |
+
"learning_rate": 0.00016114359974009096,
|
385 |
+
"loss": 0.2134,
|
386 |
+
"step": 470
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 8.421052631578947,
|
390 |
+
"grad_norm": 0.5844523310661316,
|
391 |
+
"learning_rate": 0.00015984405458089668,
|
392 |
+
"loss": 0.1927,
|
393 |
+
"step": 480
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 8.596491228070175,
|
397 |
+
"grad_norm": 0.6846328377723694,
|
398 |
+
"learning_rate": 0.0001585445094217024,
|
399 |
+
"loss": 0.1843,
|
400 |
+
"step": 490
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 8.771929824561404,
|
404 |
+
"grad_norm": 0.5246126651763916,
|
405 |
+
"learning_rate": 0.00015724496426250813,
|
406 |
+
"loss": 0.167,
|
407 |
+
"step": 500
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 8.771929824561404,
|
411 |
+
"eval_accuracy": 0.9364444444444444,
|
412 |
+
"eval_f1": 0.8354430379746836,
|
413 |
+
"eval_loss": 0.17720411717891693,
|
414 |
+
"eval_precision": 0.8325688073394495,
|
415 |
+
"eval_recall": 0.8383371824480369,
|
416 |
+
"eval_runtime": 2.7456,
|
417 |
+
"eval_samples_per_second": 81.95,
|
418 |
+
"eval_steps_per_second": 10.562,
|
419 |
+
"step": 500
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 8.947368421052632,
|
423 |
+
"grad_norm": 0.9557002782821655,
|
424 |
+
"learning_rate": 0.00015594541910331385,
|
425 |
+
"loss": 0.1752,
|
426 |
+
"step": 510
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 9.12280701754386,
|
430 |
+
"grad_norm": 1.115300178527832,
|
431 |
+
"learning_rate": 0.00015464587394411957,
|
432 |
+
"loss": 0.2,
|
433 |
+
"step": 520
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 9.298245614035087,
|
437 |
+
"grad_norm": 0.6540657877922058,
|
438 |
+
"learning_rate": 0.00015334632878492526,
|
439 |
+
"loss": 0.158,
|
440 |
+
"step": 530
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 9.473684210526315,
|
444 |
+
"grad_norm": 0.8491069078445435,
|
445 |
+
"learning_rate": 0.00015204678362573098,
|
446 |
+
"loss": 0.1813,
|
447 |
+
"step": 540
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 9.649122807017545,
|
451 |
+
"grad_norm": 1.3543705940246582,
|
452 |
+
"learning_rate": 0.0001507472384665367,
|
453 |
+
"loss": 0.1951,
|
454 |
+
"step": 550
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 9.824561403508772,
|
458 |
+
"grad_norm": 0.8627998232841492,
|
459 |
+
"learning_rate": 0.00014944769330734243,
|
460 |
+
"loss": 0.1945,
|
461 |
+
"step": 560
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 10.0,
|
465 |
+
"grad_norm": 1.2822953462600708,
|
466 |
+
"learning_rate": 0.00014814814814814815,
|
467 |
+
"loss": 0.1591,
|
468 |
+
"step": 570
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 10.175438596491228,
|
472 |
+
"grad_norm": 0.6904670596122742,
|
473 |
+
"learning_rate": 0.00014684860298895387,
|
474 |
+
"loss": 0.1545,
|
475 |
+
"step": 580
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 10.350877192982455,
|
479 |
+
"grad_norm": 1.3155221939086914,
|
480 |
+
"learning_rate": 0.0001455490578297596,
|
481 |
+
"loss": 0.1385,
|
482 |
+
"step": 590
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 10.526315789473685,
|
486 |
+
"grad_norm": 0.8683547973632812,
|
487 |
+
"learning_rate": 0.0001442495126705653,
|
488 |
+
"loss": 0.1661,
|
489 |
+
"step": 600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 10.526315789473685,
|
493 |
+
"eval_accuracy": 0.9342222222222222,
|
494 |
+
"eval_f1": 0.8258823529411765,
|
495 |
+
"eval_loss": 0.16532927751541138,
|
496 |
+
"eval_precision": 0.841726618705036,
|
497 |
+
"eval_recall": 0.8106235565819861,
|
498 |
+
"eval_runtime": 1.7784,
|
499 |
+
"eval_samples_per_second": 126.515,
|
500 |
+
"eval_steps_per_second": 16.306,
|
501 |
+
"step": 600
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 10.701754385964913,
|
505 |
+
"grad_norm": 0.7406933307647705,
|
506 |
+
"learning_rate": 0.00014294996751137103,
|
507 |
+
"loss": 0.1569,
|
508 |
+
"step": 610
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 10.87719298245614,
|
512 |
+
"grad_norm": 1.5100739002227783,
|
513 |
+
"learning_rate": 0.00014165042235217672,
|
514 |
+
"loss": 0.1873,
|
515 |
+
"step": 620
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 11.052631578947368,
|
519 |
+
"grad_norm": 0.8658424019813538,
|
520 |
+
"learning_rate": 0.00014035087719298245,
|
521 |
+
"loss": 0.1771,
|
522 |
+
"step": 630
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 11.228070175438596,
|
526 |
+
"grad_norm": 0.761426568031311,
|
527 |
+
"learning_rate": 0.00013905133203378817,
|
528 |
+
"loss": 0.1522,
|
529 |
+
"step": 640
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 11.403508771929825,
|
533 |
+
"grad_norm": 0.6994770765304565,
|
534 |
+
"learning_rate": 0.0001377517868745939,
|
535 |
+
"loss": 0.1462,
|
536 |
+
"step": 650
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 11.578947368421053,
|
540 |
+
"grad_norm": 0.6044259071350098,
|
541 |
+
"learning_rate": 0.0001364522417153996,
|
542 |
+
"loss": 0.1688,
|
543 |
+
"step": 660
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 11.75438596491228,
|
547 |
+
"grad_norm": 0.6377450227737427,
|
548 |
+
"learning_rate": 0.00013515269655620533,
|
549 |
+
"loss": 0.1726,
|
550 |
+
"step": 670
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 11.929824561403509,
|
554 |
+
"grad_norm": 0.45792627334594727,
|
555 |
+
"learning_rate": 0.00013385315139701105,
|
556 |
+
"loss": 0.1578,
|
557 |
+
"step": 680
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 12.105263157894736,
|
561 |
+
"grad_norm": 0.5658883452415466,
|
562 |
+
"learning_rate": 0.00013255360623781677,
|
563 |
+
"loss": 0.1528,
|
564 |
+
"step": 690
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 12.280701754385966,
|
568 |
+
"grad_norm": 0.568031370639801,
|
569 |
+
"learning_rate": 0.0001312540610786225,
|
570 |
+
"loss": 0.1603,
|
571 |
+
"step": 700
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 12.280701754385966,
|
575 |
+
"eval_accuracy": 0.9408888888888889,
|
576 |
+
"eval_f1": 0.8473019517795637,
|
577 |
+
"eval_loss": 0.16492225229740143,
|
578 |
+
"eval_precision": 0.8424657534246576,
|
579 |
+
"eval_recall": 0.8521939953810623,
|
580 |
+
"eval_runtime": 2.4488,
|
581 |
+
"eval_samples_per_second": 91.883,
|
582 |
+
"eval_steps_per_second": 11.843,
|
583 |
+
"step": 700
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 12.456140350877194,
|
587 |
+
"grad_norm": 0.8529219031333923,
|
588 |
+
"learning_rate": 0.0001299545159194282,
|
589 |
+
"loss": 0.1438,
|
590 |
+
"step": 710
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 12.631578947368421,
|
594 |
+
"grad_norm": 0.7960824370384216,
|
595 |
+
"learning_rate": 0.0001286549707602339,
|
596 |
+
"loss": 0.1245,
|
597 |
+
"step": 720
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 12.807017543859649,
|
601 |
+
"grad_norm": 0.8270284533500671,
|
602 |
+
"learning_rate": 0.00012748538011695908,
|
603 |
+
"loss": 0.1775,
|
604 |
+
"step": 730
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 12.982456140350877,
|
608 |
+
"grad_norm": 0.407463014125824,
|
609 |
+
"learning_rate": 0.0001261858349577648,
|
610 |
+
"loss": 0.1583,
|
611 |
+
"step": 740
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 13.157894736842104,
|
615 |
+
"grad_norm": 1.2405822277069092,
|
616 |
+
"learning_rate": 0.0001248862897985705,
|
617 |
+
"loss": 0.1412,
|
618 |
+
"step": 750
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 13.333333333333334,
|
622 |
+
"grad_norm": 0.7762990593910217,
|
623 |
+
"learning_rate": 0.00012358674463937622,
|
624 |
+
"loss": 0.137,
|
625 |
+
"step": 760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 13.508771929824562,
|
629 |
+
"grad_norm": 0.7772154808044434,
|
630 |
+
"learning_rate": 0.00012228719948018194,
|
631 |
+
"loss": 0.1618,
|
632 |
+
"step": 770
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 13.68421052631579,
|
636 |
+
"grad_norm": 0.3346017599105835,
|
637 |
+
"learning_rate": 0.00012098765432098766,
|
638 |
+
"loss": 0.1276,
|
639 |
+
"step": 780
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 13.859649122807017,
|
643 |
+
"grad_norm": 0.7661828994750977,
|
644 |
+
"learning_rate": 0.00011968810916179338,
|
645 |
+
"loss": 0.1606,
|
646 |
+
"step": 790
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 14.035087719298245,
|
650 |
+
"grad_norm": 1.2454911470413208,
|
651 |
+
"learning_rate": 0.0001183885640025991,
|
652 |
+
"loss": 0.1523,
|
653 |
+
"step": 800
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 14.035087719298245,
|
657 |
+
"eval_accuracy": 0.9466666666666667,
|
658 |
+
"eval_f1": 0.8591549295774648,
|
659 |
+
"eval_loss": 0.15682315826416016,
|
660 |
+
"eval_precision": 0.8735083532219571,
|
661 |
+
"eval_recall": 0.8452655889145496,
|
662 |
+
"eval_runtime": 1.8011,
|
663 |
+
"eval_samples_per_second": 124.926,
|
664 |
+
"eval_steps_per_second": 16.102,
|
665 |
+
"step": 800
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 14.210526315789474,
|
669 |
+
"grad_norm": 3.0044612884521484,
|
670 |
+
"learning_rate": 0.00011708901884340481,
|
671 |
+
"loss": 0.1331,
|
672 |
+
"step": 810
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 14.385964912280702,
|
676 |
+
"grad_norm": 0.7117482423782349,
|
677 |
+
"learning_rate": 0.00011578947368421053,
|
678 |
+
"loss": 0.1619,
|
679 |
+
"step": 820
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 14.56140350877193,
|
683 |
+
"grad_norm": 0.6939218044281006,
|
684 |
+
"learning_rate": 0.00011448992852501626,
|
685 |
+
"loss": 0.1531,
|
686 |
+
"step": 830
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 14.736842105263158,
|
690 |
+
"grad_norm": 0.5622960329055786,
|
691 |
+
"learning_rate": 0.00011319038336582198,
|
692 |
+
"loss": 0.131,
|
693 |
+
"step": 840
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 14.912280701754385,
|
697 |
+
"grad_norm": 0.9399430155754089,
|
698 |
+
"learning_rate": 0.0001118908382066277,
|
699 |
+
"loss": 0.1276,
|
700 |
+
"step": 850
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 15.087719298245615,
|
704 |
+
"grad_norm": 1.6480320692062378,
|
705 |
+
"learning_rate": 0.0001105912930474334,
|
706 |
+
"loss": 0.1656,
|
707 |
+
"step": 860
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 15.263157894736842,
|
711 |
+
"grad_norm": 0.7238647937774658,
|
712 |
+
"learning_rate": 0.00010929174788823913,
|
713 |
+
"loss": 0.1261,
|
714 |
+
"step": 870
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 15.43859649122807,
|
718 |
+
"grad_norm": 1.0423846244812012,
|
719 |
+
"learning_rate": 0.00010799220272904485,
|
720 |
+
"loss": 0.1328,
|
721 |
+
"step": 880
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 15.614035087719298,
|
725 |
+
"grad_norm": 1.1374431848526,
|
726 |
+
"learning_rate": 0.00010669265756985057,
|
727 |
+
"loss": 0.1427,
|
728 |
+
"step": 890
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 15.789473684210526,
|
732 |
+
"grad_norm": 0.7375030517578125,
|
733 |
+
"learning_rate": 0.00010539311241065628,
|
734 |
+
"loss": 0.1506,
|
735 |
+
"step": 900
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 15.789473684210526,
|
739 |
+
"eval_accuracy": 0.9431111111111111,
|
740 |
+
"eval_f1": 0.8494117647058823,
|
741 |
+
"eval_loss": 0.15481138229370117,
|
742 |
+
"eval_precision": 0.8657074340527577,
|
743 |
+
"eval_recall": 0.8337182448036952,
|
744 |
+
"eval_runtime": 1.8243,
|
745 |
+
"eval_samples_per_second": 123.334,
|
746 |
+
"eval_steps_per_second": 15.896,
|
747 |
+
"step": 900
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 15.964912280701755,
|
751 |
+
"grad_norm": 0.7035567164421082,
|
752 |
+
"learning_rate": 0.000104093567251462,
|
753 |
+
"loss": 0.1324,
|
754 |
+
"step": 910
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 16.140350877192983,
|
758 |
+
"grad_norm": 0.6969211101531982,
|
759 |
+
"learning_rate": 0.00010279402209226772,
|
760 |
+
"loss": 0.1257,
|
761 |
+
"step": 920
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 16.31578947368421,
|
765 |
+
"grad_norm": 0.3633826673030853,
|
766 |
+
"learning_rate": 0.00010149447693307344,
|
767 |
+
"loss": 0.1306,
|
768 |
+
"step": 930
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 16.49122807017544,
|
772 |
+
"grad_norm": 0.8118802309036255,
|
773 |
+
"learning_rate": 0.00010019493177387915,
|
774 |
+
"loss": 0.1091,
|
775 |
+
"step": 940
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 16.666666666666668,
|
779 |
+
"grad_norm": 0.6684471964836121,
|
780 |
+
"learning_rate": 9.889538661468485e-05,
|
781 |
+
"loss": 0.1323,
|
782 |
+
"step": 950
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 16.842105263157894,
|
786 |
+
"grad_norm": 0.6080668568611145,
|
787 |
+
"learning_rate": 9.759584145549058e-05,
|
788 |
+
"loss": 0.1168,
|
789 |
+
"step": 960
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 17.017543859649123,
|
793 |
+
"grad_norm": 0.7799493670463562,
|
794 |
+
"learning_rate": 9.62962962962963e-05,
|
795 |
+
"loss": 0.141,
|
796 |
+
"step": 970
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 17.19298245614035,
|
800 |
+
"grad_norm": 0.5670738816261292,
|
801 |
+
"learning_rate": 9.499675113710202e-05,
|
802 |
+
"loss": 0.1244,
|
803 |
+
"step": 980
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 17.36842105263158,
|
807 |
+
"grad_norm": 0.9652756452560425,
|
808 |
+
"learning_rate": 9.369720597790773e-05,
|
809 |
+
"loss": 0.1354,
|
810 |
+
"step": 990
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 17.54385964912281,
|
814 |
+
"grad_norm": 0.8537412881851196,
|
815 |
+
"learning_rate": 9.239766081871345e-05,
|
816 |
+
"loss": 0.1485,
|
817 |
+
"step": 1000
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 17.54385964912281,
|
821 |
+
"eval_accuracy": 0.9444444444444444,
|
822 |
+
"eval_f1": 0.8544819557625145,
|
823 |
+
"eval_loss": 0.15389865636825562,
|
824 |
+
"eval_precision": 0.8615023474178404,
|
825 |
+
"eval_recall": 0.8475750577367206,
|
826 |
+
"eval_runtime": 1.7887,
|
827 |
+
"eval_samples_per_second": 125.789,
|
828 |
+
"eval_steps_per_second": 16.213,
|
829 |
+
"step": 1000
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 17.719298245614034,
|
833 |
+
"grad_norm": 0.9258742928504944,
|
834 |
+
"learning_rate": 9.109811565951917e-05,
|
835 |
+
"loss": 0.1284,
|
836 |
+
"step": 1010
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 17.894736842105264,
|
840 |
+
"grad_norm": 0.6817509531974792,
|
841 |
+
"learning_rate": 8.979857050032489e-05,
|
842 |
+
"loss": 0.1226,
|
843 |
+
"step": 1020
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 18.07017543859649,
|
847 |
+
"grad_norm": 0.8437041640281677,
|
848 |
+
"learning_rate": 8.849902534113061e-05,
|
849 |
+
"loss": 0.1527,
|
850 |
+
"step": 1030
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 18.24561403508772,
|
854 |
+
"grad_norm": 1.2362749576568604,
|
855 |
+
"learning_rate": 8.719948018193632e-05,
|
856 |
+
"loss": 0.1224,
|
857 |
+
"step": 1040
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 18.42105263157895,
|
861 |
+
"grad_norm": 0.4136218726634979,
|
862 |
+
"learning_rate": 8.589993502274204e-05,
|
863 |
+
"loss": 0.1293,
|
864 |
+
"step": 1050
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 18.596491228070175,
|
868 |
+
"grad_norm": 0.8913040161132812,
|
869 |
+
"learning_rate": 8.460038986354776e-05,
|
870 |
+
"loss": 0.1305,
|
871 |
+
"step": 1060
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 18.771929824561404,
|
875 |
+
"grad_norm": 1.0768448114395142,
|
876 |
+
"learning_rate": 8.330084470435348e-05,
|
877 |
+
"loss": 0.1134,
|
878 |
+
"step": 1070
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 18.94736842105263,
|
882 |
+
"grad_norm": 0.9289010763168335,
|
883 |
+
"learning_rate": 8.200129954515919e-05,
|
884 |
+
"loss": 0.1551,
|
885 |
+
"step": 1080
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 19.12280701754386,
|
889 |
+
"grad_norm": 0.4481465220451355,
|
890 |
+
"learning_rate": 8.070175438596491e-05,
|
891 |
+
"loss": 0.1263,
|
892 |
+
"step": 1090
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 19.29824561403509,
|
896 |
+
"grad_norm": 0.7408900260925293,
|
897 |
+
"learning_rate": 7.940220922677063e-05,
|
898 |
+
"loss": 0.1263,
|
899 |
+
"step": 1100
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 19.29824561403509,
|
903 |
+
"eval_accuracy": 0.944,
|
904 |
+
"eval_f1": 0.8534883720930233,
|
905 |
+
"eval_loss": 0.15210777521133423,
|
906 |
+
"eval_precision": 0.8594847775175644,
|
907 |
+
"eval_recall": 0.8475750577367206,
|
908 |
+
"eval_runtime": 1.7885,
|
909 |
+
"eval_samples_per_second": 125.802,
|
910 |
+
"eval_steps_per_second": 16.214,
|
911 |
+
"step": 1100
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 19.473684210526315,
|
915 |
+
"grad_norm": 0.8939012289047241,
|
916 |
+
"learning_rate": 7.810266406757635e-05,
|
917 |
+
"loss": 0.1206,
|
918 |
+
"step": 1110
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 19.649122807017545,
|
922 |
+
"grad_norm": 0.6809560656547546,
|
923 |
+
"learning_rate": 7.680311890838207e-05,
|
924 |
+
"loss": 0.1225,
|
925 |
+
"step": 1120
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 19.82456140350877,
|
929 |
+
"grad_norm": 1.1481623649597168,
|
930 |
+
"learning_rate": 7.550357374918778e-05,
|
931 |
+
"loss": 0.1291,
|
932 |
+
"step": 1130
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 20.0,
|
936 |
+
"grad_norm": 2.0011980533599854,
|
937 |
+
"learning_rate": 7.42040285899935e-05,
|
938 |
+
"loss": 0.1482,
|
939 |
+
"step": 1140
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 20.17543859649123,
|
943 |
+
"grad_norm": 0.6619019508361816,
|
944 |
+
"learning_rate": 7.290448343079922e-05,
|
945 |
+
"loss": 0.1123,
|
946 |
+
"step": 1150
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 20.350877192982455,
|
950 |
+
"grad_norm": 0.796700656414032,
|
951 |
+
"learning_rate": 7.160493827160494e-05,
|
952 |
+
"loss": 0.1166,
|
953 |
+
"step": 1160
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 20.526315789473685,
|
957 |
+
"grad_norm": 0.9634900689125061,
|
958 |
+
"learning_rate": 7.030539311241065e-05,
|
959 |
+
"loss": 0.1263,
|
960 |
+
"step": 1170
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 20.70175438596491,
|
964 |
+
"grad_norm": 0.505535900592804,
|
965 |
+
"learning_rate": 6.900584795321637e-05,
|
966 |
+
"loss": 0.1117,
|
967 |
+
"step": 1180
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 20.87719298245614,
|
971 |
+
"grad_norm": 0.5166471600532532,
|
972 |
+
"learning_rate": 6.770630279402209e-05,
|
973 |
+
"loss": 0.1279,
|
974 |
+
"step": 1190
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 21.05263157894737,
|
978 |
+
"grad_norm": 1.2773476839065552,
|
979 |
+
"learning_rate": 6.640675763482781e-05,
|
980 |
+
"loss": 0.1444,
|
981 |
+
"step": 1200
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 21.05263157894737,
|
985 |
+
"eval_accuracy": 0.9417777777777778,
|
986 |
+
"eval_f1": 0.8471411901983664,
|
987 |
+
"eval_loss": 0.155166357755661,
|
988 |
+
"eval_precision": 0.8561320754716981,
|
989 |
+
"eval_recall": 0.8383371824480369,
|
990 |
+
"eval_runtime": 2.37,
|
991 |
+
"eval_samples_per_second": 94.937,
|
992 |
+
"eval_steps_per_second": 12.236,
|
993 |
+
"step": 1200
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 21.228070175438596,
|
997 |
+
"grad_norm": 0.793021559715271,
|
998 |
+
"learning_rate": 6.510721247563352e-05,
|
999 |
+
"loss": 0.1168,
|
1000 |
+
"step": 1210
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"epoch": 21.403508771929825,
|
1004 |
+
"grad_norm": 1.2551689147949219,
|
1005 |
+
"learning_rate": 6.380766731643924e-05,
|
1006 |
+
"loss": 0.1089,
|
1007 |
+
"step": 1220
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 21.57894736842105,
|
1011 |
+
"grad_norm": 0.6803563237190247,
|
1012 |
+
"learning_rate": 6.250812215724496e-05,
|
1013 |
+
"loss": 0.1186,
|
1014 |
+
"step": 1230
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 21.75438596491228,
|
1018 |
+
"grad_norm": 1.2632770538330078,
|
1019 |
+
"learning_rate": 6.120857699805068e-05,
|
1020 |
+
"loss": 0.1116,
|
1021 |
+
"step": 1240
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 21.92982456140351,
|
1025 |
+
"grad_norm": 0.525141716003418,
|
1026 |
+
"learning_rate": 5.99090318388564e-05,
|
1027 |
+
"loss": 0.0979,
|
1028 |
+
"step": 1250
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 22.105263157894736,
|
1032 |
+
"grad_norm": 0.5942980647087097,
|
1033 |
+
"learning_rate": 5.860948667966212e-05,
|
1034 |
+
"loss": 0.1483,
|
1035 |
+
"step": 1260
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 22.280701754385966,
|
1039 |
+
"grad_norm": 1.0624207258224487,
|
1040 |
+
"learning_rate": 5.7309941520467835e-05,
|
1041 |
+
"loss": 0.1155,
|
1042 |
+
"step": 1270
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 22.45614035087719,
|
1046 |
+
"grad_norm": 0.6244792938232422,
|
1047 |
+
"learning_rate": 5.6010396361273556e-05,
|
1048 |
+
"loss": 0.1159,
|
1049 |
+
"step": 1280
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 22.63157894736842,
|
1053 |
+
"grad_norm": 1.9767743349075317,
|
1054 |
+
"learning_rate": 5.471085120207927e-05,
|
1055 |
+
"loss": 0.1165,
|
1056 |
+
"step": 1290
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 22.80701754385965,
|
1060 |
+
"grad_norm": 2.270113468170166,
|
1061 |
+
"learning_rate": 5.341130604288499e-05,
|
1062 |
+
"loss": 0.1133,
|
1063 |
+
"step": 1300
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 22.80701754385965,
|
1067 |
+
"eval_accuracy": 0.9448888888888889,
|
1068 |
+
"eval_f1": 0.8561484918793504,
|
1069 |
+
"eval_loss": 0.1531468778848648,
|
1070 |
+
"eval_precision": 0.8601398601398601,
|
1071 |
+
"eval_recall": 0.8521939953810623,
|
1072 |
+
"eval_runtime": 4.5112,
|
1073 |
+
"eval_samples_per_second": 49.875,
|
1074 |
+
"eval_steps_per_second": 6.428,
|
1075 |
+
"step": 1300
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 22.982456140350877,
|
1079 |
+
"grad_norm": 2.3252851963043213,
|
1080 |
+
"learning_rate": 5.2111760883690706e-05,
|
1081 |
+
"loss": 0.1018,
|
1082 |
+
"step": 1310
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 23.157894736842106,
|
1086 |
+
"grad_norm": 1.3282454013824463,
|
1087 |
+
"learning_rate": 5.081221572449643e-05,
|
1088 |
+
"loss": 0.1194,
|
1089 |
+
"step": 1320
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 23.333333333333332,
|
1093 |
+
"grad_norm": 0.652642548084259,
|
1094 |
+
"learning_rate": 4.951267056530214e-05,
|
1095 |
+
"loss": 0.1016,
|
1096 |
+
"step": 1330
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 23.50877192982456,
|
1100 |
+
"grad_norm": 1.584074854850769,
|
1101 |
+
"learning_rate": 4.821312540610786e-05,
|
1102 |
+
"loss": 0.1109,
|
1103 |
+
"step": 1340
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 23.68421052631579,
|
1107 |
+
"grad_norm": 0.5799722075462341,
|
1108 |
+
"learning_rate": 4.691358024691358e-05,
|
1109 |
+
"loss": 0.0901,
|
1110 |
+
"step": 1350
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 23.859649122807017,
|
1114 |
+
"grad_norm": 1.9589979648590088,
|
1115 |
+
"learning_rate": 4.56140350877193e-05,
|
1116 |
+
"loss": 0.1195,
|
1117 |
+
"step": 1360
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 24.035087719298247,
|
1121 |
+
"grad_norm": 0.784710705280304,
|
1122 |
+
"learning_rate": 4.431448992852502e-05,
|
1123 |
+
"loss": 0.1318,
|
1124 |
+
"step": 1370
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 24.210526315789473,
|
1128 |
+
"grad_norm": 1.0715792179107666,
|
1129 |
+
"learning_rate": 4.301494476933073e-05,
|
1130 |
+
"loss": 0.1236,
|
1131 |
+
"step": 1380
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 24.385964912280702,
|
1135 |
+
"grad_norm": 0.8761755228042603,
|
1136 |
+
"learning_rate": 4.1715399610136454e-05,
|
1137 |
+
"loss": 0.1076,
|
1138 |
+
"step": 1390
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 24.56140350877193,
|
1142 |
+
"grad_norm": 0.8874859809875488,
|
1143 |
+
"learning_rate": 4.041585445094217e-05,
|
1144 |
+
"loss": 0.1019,
|
1145 |
+
"step": 1400
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 24.56140350877193,
|
1149 |
+
"eval_accuracy": 0.9431111111111111,
|
1150 |
+
"eval_f1": 0.8490566037735849,
|
1151 |
+
"eval_loss": 0.15768744051456451,
|
1152 |
+
"eval_precision": 0.8674698795180723,
|
1153 |
+
"eval_recall": 0.8314087759815243,
|
1154 |
+
"eval_runtime": 1.817,
|
1155 |
+
"eval_samples_per_second": 123.828,
|
1156 |
+
"eval_steps_per_second": 15.96,
|
1157 |
+
"step": 1400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 24.736842105263158,
|
1161 |
+
"grad_norm": 0.569615364074707,
|
1162 |
+
"learning_rate": 3.911630929174789e-05,
|
1163 |
+
"loss": 0.1114,
|
1164 |
+
"step": 1410
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 24.912280701754387,
|
1168 |
+
"grad_norm": 0.4636388123035431,
|
1169 |
+
"learning_rate": 3.7816764132553604e-05,
|
1170 |
+
"loss": 0.1016,
|
1171 |
+
"step": 1420
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 25.087719298245613,
|
1175 |
+
"grad_norm": 0.7966068983078003,
|
1176 |
+
"learning_rate": 3.6517218973359325e-05,
|
1177 |
+
"loss": 0.1181,
|
1178 |
+
"step": 1430
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 25.263157894736842,
|
1182 |
+
"grad_norm": 0.7331326603889465,
|
1183 |
+
"learning_rate": 3.521767381416504e-05,
|
1184 |
+
"loss": 0.1037,
|
1185 |
+
"step": 1440
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 25.43859649122807,
|
1189 |
+
"grad_norm": 1.1376439332962036,
|
1190 |
+
"learning_rate": 3.391812865497076e-05,
|
1191 |
+
"loss": 0.091,
|
1192 |
+
"step": 1450
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 25.614035087719298,
|
1196 |
+
"grad_norm": 0.43491020798683167,
|
1197 |
+
"learning_rate": 3.2618583495776475e-05,
|
1198 |
+
"loss": 0.102,
|
1199 |
+
"step": 1460
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 25.789473684210527,
|
1203 |
+
"grad_norm": 0.9410120844841003,
|
1204 |
+
"learning_rate": 3.1319038336582196e-05,
|
1205 |
+
"loss": 0.1108,
|
1206 |
+
"step": 1470
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 25.964912280701753,
|
1210 |
+
"grad_norm": 0.9321810603141785,
|
1211 |
+
"learning_rate": 3.0019493177387914e-05,
|
1212 |
+
"loss": 0.1059,
|
1213 |
+
"step": 1480
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 26.140350877192983,
|
1217 |
+
"grad_norm": 0.5571371912956238,
|
1218 |
+
"learning_rate": 2.871994801819363e-05,
|
1219 |
+
"loss": 0.0926,
|
1220 |
+
"step": 1490
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 26.31578947368421,
|
1224 |
+
"grad_norm": 1.9081007242202759,
|
1225 |
+
"learning_rate": 2.742040285899935e-05,
|
1226 |
+
"loss": 0.1141,
|
1227 |
+
"step": 1500
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 26.31578947368421,
|
1231 |
+
"eval_accuracy": 0.9413333333333334,
|
1232 |
+
"eval_f1": 0.8472222222222222,
|
1233 |
+
"eval_loss": 0.15601032972335815,
|
1234 |
+
"eval_precision": 0.8491879350348028,
|
1235 |
+
"eval_recall": 0.8452655889145496,
|
1236 |
+
"eval_runtime": 1.867,
|
1237 |
+
"eval_samples_per_second": 120.511,
|
1238 |
+
"eval_steps_per_second": 15.533,
|
1239 |
+
"step": 1500
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 26.49122807017544,
|
1243 |
+
"grad_norm": 0.8356673121452332,
|
1244 |
+
"learning_rate": 2.6120857699805067e-05,
|
1245 |
+
"loss": 0.1077,
|
1246 |
+
"step": 1510
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 26.666666666666668,
|
1250 |
+
"grad_norm": 1.3644295930862427,
|
1251 |
+
"learning_rate": 2.4821312540610784e-05,
|
1252 |
+
"loss": 0.1212,
|
1253 |
+
"step": 1520
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 26.842105263157894,
|
1257 |
+
"grad_norm": 0.779222309589386,
|
1258 |
+
"learning_rate": 2.3521767381416506e-05,
|
1259 |
+
"loss": 0.1229,
|
1260 |
+
"step": 1530
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 27.017543859649123,
|
1264 |
+
"grad_norm": 0.5873481631278992,
|
1265 |
+
"learning_rate": 2.2222222222222223e-05,
|
1266 |
+
"loss": 0.0998,
|
1267 |
+
"step": 1540
|
1268 |
+
},
|
1269 |
+
{
|
1270 |
+
"epoch": 27.19298245614035,
|
1271 |
+
"grad_norm": 0.9948704242706299,
|
1272 |
+
"learning_rate": 2.092267706302794e-05,
|
1273 |
+
"loss": 0.1435,
|
1274 |
+
"step": 1550
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 27.36842105263158,
|
1278 |
+
"grad_norm": 0.32820120453834534,
|
1279 |
+
"learning_rate": 1.962313190383366e-05,
|
1280 |
+
"loss": 0.0992,
|
1281 |
+
"step": 1560
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 27.54385964912281,
|
1285 |
+
"grad_norm": 1.0797744989395142,
|
1286 |
+
"learning_rate": 1.8323586744639376e-05,
|
1287 |
+
"loss": 0.1095,
|
1288 |
+
"step": 1570
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"epoch": 27.719298245614034,
|
1292 |
+
"grad_norm": 1.5036197900772095,
|
1293 |
+
"learning_rate": 1.7024041585445094e-05,
|
1294 |
+
"loss": 0.119,
|
1295 |
+
"step": 1580
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 27.894736842105264,
|
1299 |
+
"grad_norm": 1.0871007442474365,
|
1300 |
+
"learning_rate": 1.5724496426250812e-05,
|
1301 |
+
"loss": 0.0974,
|
1302 |
+
"step": 1590
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 28.07017543859649,
|
1306 |
+
"grad_norm": 0.6861986517906189,
|
1307 |
+
"learning_rate": 1.442495126705653e-05,
|
1308 |
+
"loss": 0.1087,
|
1309 |
+
"step": 1600
|
1310 |
+
},
|
1311 |
+
{
|
1312 |
+
"epoch": 28.07017543859649,
|
1313 |
+
"eval_accuracy": 0.9422222222222222,
|
1314 |
+
"eval_f1": 0.8491879350348028,
|
1315 |
+
"eval_loss": 0.15734025835990906,
|
1316 |
+
"eval_precision": 0.8531468531468531,
|
1317 |
+
"eval_recall": 0.8452655889145496,
|
1318 |
+
"eval_runtime": 3.5904,
|
1319 |
+
"eval_samples_per_second": 62.668,
|
1320 |
+
"eval_steps_per_second": 8.077,
|
1321 |
+
"step": 1600
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 28.24561403508772,
|
1325 |
+
"grad_norm": 1.5399742126464844,
|
1326 |
+
"learning_rate": 1.3125406107862247e-05,
|
1327 |
+
"loss": 0.1243,
|
1328 |
+
"step": 1610
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 28.42105263157895,
|
1332 |
+
"grad_norm": 0.7721771001815796,
|
1333 |
+
"learning_rate": 1.1825860948667967e-05,
|
1334 |
+
"loss": 0.0965,
|
1335 |
+
"step": 1620
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 28.596491228070175,
|
1339 |
+
"grad_norm": 1.040131688117981,
|
1340 |
+
"learning_rate": 1.0526315789473684e-05,
|
1341 |
+
"loss": 0.1133,
|
1342 |
+
"step": 1630
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 28.771929824561404,
|
1346 |
+
"grad_norm": 0.9755656123161316,
|
1347 |
+
"learning_rate": 9.226770630279402e-06,
|
1348 |
+
"loss": 0.0885,
|
1349 |
+
"step": 1640
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 28.94736842105263,
|
1353 |
+
"grad_norm": 0.5838367342948914,
|
1354 |
+
"learning_rate": 7.92722547108512e-06,
|
1355 |
+
"loss": 0.1134,
|
1356 |
+
"step": 1650
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 29.12280701754386,
|
1360 |
+
"grad_norm": 1.698116421699524,
|
1361 |
+
"learning_rate": 6.6276803118908384e-06,
|
1362 |
+
"loss": 0.1278,
|
1363 |
+
"step": 1660
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 29.29824561403509,
|
1367 |
+
"grad_norm": 0.581572413444519,
|
1368 |
+
"learning_rate": 5.328135152696556e-06,
|
1369 |
+
"loss": 0.1209,
|
1370 |
+
"step": 1670
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 29.473684210526315,
|
1374 |
+
"grad_norm": 0.4100797772407532,
|
1375 |
+
"learning_rate": 4.028589993502274e-06,
|
1376 |
+
"loss": 0.1108,
|
1377 |
+
"step": 1680
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 29.649122807017545,
|
1381 |
+
"grad_norm": 1.5013538599014282,
|
1382 |
+
"learning_rate": 2.729044834307992e-06,
|
1383 |
+
"loss": 0.1195,
|
1384 |
+
"step": 1690
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 29.82456140350877,
|
1388 |
+
"grad_norm": 1.0121512413024902,
|
1389 |
+
"learning_rate": 1.4294996751137102e-06,
|
1390 |
+
"loss": 0.1015,
|
1391 |
+
"step": 1700
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 29.82456140350877,
|
1395 |
+
"eval_accuracy": 0.9422222222222222,
|
1396 |
+
"eval_f1": 0.8488372093023255,
|
1397 |
+
"eval_loss": 0.15452326834201813,
|
1398 |
+
"eval_precision": 0.8548009367681498,
|
1399 |
+
"eval_recall": 0.8429561200923787,
|
1400 |
+
"eval_runtime": 1.8193,
|
1401 |
+
"eval_samples_per_second": 123.672,
|
1402 |
+
"eval_steps_per_second": 15.94,
|
1403 |
+
"step": 1700
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 30.0,
|
1407 |
+
"grad_norm": 2.770343780517578,
|
1408 |
+
"learning_rate": 1.299545159194282e-07,
|
1409 |
+
"loss": 0.1342,
|
1410 |
+
"step": 1710
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 30.0,
|
1414 |
+
"step": 1710,
|
1415 |
+
"total_flos": 1.77124415883264e+17,
|
1416 |
+
"train_loss": 0.20865077226482637,
|
1417 |
+
"train_runtime": 373.9101,
|
1418 |
+
"train_samples_per_second": 72.21,
|
1419 |
+
"train_steps_per_second": 4.573
|
1420 |
+
}
|
1421 |
+
],
|
1422 |
+
"logging_steps": 10,
|
1423 |
+
"max_steps": 1710,
|
1424 |
+
"num_input_tokens_seen": 0,
|
1425 |
+
"num_train_epochs": 30,
|
1426 |
+
"save_steps": 500,
|
1427 |
+
"stateful_callbacks": {
|
1428 |
+
"TrainerControl": {
|
1429 |
+
"args": {
|
1430 |
+
"should_epoch_stop": false,
|
1431 |
+
"should_evaluate": false,
|
1432 |
+
"should_log": false,
|
1433 |
+
"should_save": true,
|
1434 |
+
"should_training_stop": true
|
1435 |
+
},
|
1436 |
+
"attributes": {}
|
1437 |
+
}
|
1438 |
+
},
|
1439 |
+
"total_flos": 1.77124415883264e+17,
|
1440 |
+
"train_batch_size": 16,
|
1441 |
+
"trial_name": null,
|
1442 |
+
"trial_params": null
|
1443 |
+
}
|