Commit
·
a6e68cb
1
Parent(s):
0db5bc0
Add evaluation results and output files to model card
Browse files- README.md +6 -6
- checkpoint-8/model.safetensors +1 -1
- checkpoint-8/optimizer.pt +1 -1
- checkpoint-8/scheduler.pt +1 -1
- checkpoint-8/trainer_state.json +39 -39
- checkpoint-8/training_args.bin +2 -2
- model.safetensors +1 -1
- pr_curve.png +0 -0
- roc_curve.png +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,18 +5,18 @@ tags:
|
|
5 |
- model
|
6 |
- evaluation
|
7 |
metrics:
|
8 |
-
- average_precision: 0.
|
9 |
-
- roc_auc: 0.
|
10 |
-
- best threshold according to F1: 0.
|
11 |
---
|
12 |
|
13 |
# Binary Classification Model
|
14 |
|
15 |
## Evaluation Results
|
16 |
|
17 |
-
**Average Precision:** 0.
|
18 |
-
**ROC AUC:** 0.
|
19 |
-
**best threshold according to F1: 0.
|
20 |
|
21 |
|
22 |
## Visualizations
|
|
|
5 |
- model
|
6 |
- evaluation
|
7 |
metrics:
|
8 |
+
- average_precision: 0.95
|
9 |
+
- roc_auc: 0.93
|
10 |
+
- best threshold according to F1: 0.44
|
11 |
---
|
12 |
|
13 |
# Binary Classification Model
|
14 |
|
15 |
## Evaluation Results
|
16 |
|
17 |
+
**Average Precision:** 0.95
|
18 |
+
**ROC AUC:** 0.93
|
19 |
+
**best threshold according to F1: 0.44
|
20 |
|
21 |
|
22 |
## Visualizations
|
checkpoint-8/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8760128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fced4ab76217d28bcd7de9a83e6fc619c1576a41165fd3b91280418c68ced5d1
|
3 |
size 8760128
|
checkpoint-8/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17564858
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f581e008d5914466c5395d23b18e45299d3ac0fb3aeef93ba811aaab6c7114b
|
3 |
size 17564858
|
checkpoint-8/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:698379ffc8ebaa82bdd977f5c57de7891b341867f48cc2cee1320c2e7fe9fa12
|
3 |
size 1064
|
checkpoint-8/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "/tmp/logs/binary_classification_model_v3.1.5_Junction_batch2/checkpoint-8",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,85 +10,85 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.13333333333333333,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss": 0.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.26666666666666666,
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate": 0.
|
22 |
-
"loss": 0.
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.4,
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate": 0.
|
29 |
-
"loss": 0.
|
30 |
"step": 3
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.5333333333333333,
|
34 |
-
"grad_norm":
|
35 |
-
"learning_rate": 0.
|
36 |
-
"loss": 0.
|
37 |
"step": 4
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.6666666666666666,
|
41 |
-
"grad_norm":
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss": 0.
|
44 |
"step": 5
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.8,
|
48 |
-
"grad_norm":
|
49 |
-
"learning_rate": 0.
|
50 |
-
"loss": 0.
|
51 |
"step": 6
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.9333333333333333,
|
55 |
-
"grad_norm":
|
56 |
-
"learning_rate": 0.
|
57 |
-
"loss": 0.
|
58 |
"step": 7
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.0,
|
62 |
-
"grad_norm":
|
63 |
-
"learning_rate": 0.
|
64 |
-
"loss": 0.
|
65 |
"step": 8
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.0,
|
69 |
-
"eval_accuracy": 0.
|
70 |
-
"eval_best_threshold": 0.
|
71 |
-
"eval_f1": 0.
|
72 |
-
"eval_loss": 0.
|
73 |
-
"eval_pr_auc": 0.
|
74 |
-
"eval_precision": 0.
|
75 |
-
"eval_recall": 0.
|
76 |
-
"eval_roc_auc": 0.
|
77 |
-
"eval_runtime": 2.
|
78 |
-
"eval_samples_per_second":
|
79 |
-
"eval_steps_per_second":
|
80 |
"step": 8
|
81 |
}
|
82 |
],
|
83 |
"logging_steps": 1,
|
84 |
-
"max_steps":
|
85 |
"num_input_tokens_seen": 0,
|
86 |
-
"num_train_epochs":
|
87 |
"save_steps": 500,
|
88 |
"stateful_callbacks": {
|
89 |
"EarlyStoppingCallback": {
|
90 |
"args": {
|
91 |
-
"early_stopping_patience":
|
92 |
"early_stopping_threshold": 0.0
|
93 |
},
|
94 |
"attributes": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8425618780301097,
|
3 |
"best_model_checkpoint": "/tmp/logs/binary_classification_model_v3.1.5_Junction_batch2/checkpoint-8",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.13333333333333333,
|
13 |
+
"grad_norm": 13324.8955078125,
|
14 |
+
"learning_rate": 0.00014285714285714287,
|
15 |
+
"loss": 0.3452,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.26666666666666666,
|
20 |
+
"grad_norm": 13969.9384765625,
|
21 |
+
"learning_rate": 0.00028571428571428574,
|
22 |
+
"loss": 0.3389,
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.4,
|
27 |
+
"grad_norm": 25136.65234375,
|
28 |
+
"learning_rate": 0.0004285714285714286,
|
29 |
+
"loss": 0.3301,
|
30 |
"step": 3
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.5333333333333333,
|
34 |
+
"grad_norm": 21701.81640625,
|
35 |
+
"learning_rate": 0.0005714285714285715,
|
36 |
+
"loss": 0.3312,
|
37 |
"step": 4
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.6666666666666666,
|
41 |
+
"grad_norm": 24685.49609375,
|
42 |
+
"learning_rate": 0.0007142857142857143,
|
43 |
+
"loss": 0.323,
|
44 |
"step": 5
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.8,
|
48 |
+
"grad_norm": 45404.9921875,
|
49 |
+
"learning_rate": 0.0008571428571428572,
|
50 |
+
"loss": 0.358,
|
51 |
"step": 6
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.9333333333333333,
|
55 |
+
"grad_norm": 20938.6328125,
|
56 |
+
"learning_rate": 0.001,
|
57 |
+
"loss": 0.3457,
|
58 |
"step": 7
|
59 |
},
|
60 |
{
|
61 |
"epoch": 1.0,
|
62 |
+
"grad_norm": 30029.5546875,
|
63 |
+
"learning_rate": 0.001142857142857143,
|
64 |
+
"loss": 0.1635,
|
65 |
"step": 8
|
66 |
},
|
67 |
{
|
68 |
"epoch": 1.0,
|
69 |
+
"eval_accuracy": 0.8318342872717361,
|
70 |
+
"eval_best_threshold": 0.3127627372741699,
|
71 |
+
"eval_f1": 0.8425618780301097,
|
72 |
+
"eval_loss": 0.368960976600647,
|
73 |
+
"eval_pr_auc": 0.9260693646178895,
|
74 |
+
"eval_precision": 0.8177315502724121,
|
75 |
+
"eval_recall": 0.8689473684210526,
|
76 |
+
"eval_roc_auc": 0.9189140459968462,
|
77 |
+
"eval_runtime": 2.7482,
|
78 |
+
"eval_samples_per_second": 1335.042,
|
79 |
+
"eval_steps_per_second": 2.911,
|
80 |
"step": 8
|
81 |
}
|
82 |
],
|
83 |
"logging_steps": 1,
|
84 |
+
"max_steps": 3500,
|
85 |
"num_input_tokens_seen": 0,
|
86 |
+
"num_train_epochs": 500,
|
87 |
"save_steps": 500,
|
88 |
"stateful_callbacks": {
|
89 |
"EarlyStoppingCallback": {
|
90 |
"args": {
|
91 |
+
"early_stopping_patience": 50,
|
92 |
"early_stopping_threshold": 0.0
|
93 |
},
|
94 |
"attributes": {
|
checkpoint-8/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4056f3d0beca21dab5fc55a93dc339d6de9a32168cdb0039f8dffef443e6b27f
|
3 |
+
size 5432
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8760128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c12e90cdacbeb9a95697e94c9c5cd32d029cf14517dd16c5b49332d0eac0c61
|
3 |
size 8760128
|
pr_curve.png
CHANGED
![]() |
![]() |
roc_curve.png
CHANGED
![]() |
![]() |
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4056f3d0beca21dab5fc55a93dc339d6de9a32168cdb0039f8dffef443e6b27f
|
3 |
size 5432
|