yaniseuranova
commited on
Commit
•
541793e
1
Parent(s):
aea7afb
🍻 cheers
Browse files- README.md +8 -1
- all_results.json +8 -8
- eval_results.json +4 -4
- runs/Aug30_09-27-15_7e2de4304170/events.out.tfevents.1725010090.7e2de4304170 +3 -0
- train_results.json +4 -4
- trainer_state.json +20 -20
README.md
CHANGED
@@ -2,7 +2,11 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: vit-base-beans
|
8 |
results: []
|
@@ -13,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# vit-base-beans
|
15 |
|
16 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
5 |
+
- image-classification
|
6 |
+
- vision
|
7 |
- generated_from_trainer
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
model-index:
|
11 |
- name: vit-base-beans
|
12 |
results: []
|
|
|
17 |
|
18 |
# vit-base-beans
|
19 |
|
20 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0096
|
23 |
+
- Accuracy: 1.0
|
24 |
|
25 |
## Model description
|
26 |
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 2.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 4.
|
8 |
"total_flos": 2.5417372593586176e+16,
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 2.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.009642996825277805,
|
5 |
+
"eval_runtime": 2.6862,
|
6 |
+
"eval_samples_per_second": 30.526,
|
7 |
+
"eval_steps_per_second": 4.095,
|
8 |
"total_flos": 2.5417372593586176e+16,
|
9 |
+
"train_loss": 0.15871779123942056,
|
10 |
+
"train_runtime": 30.4881,
|
11 |
+
"train_samples_per_second": 10.758,
|
12 |
+
"train_steps_per_second": 2.755
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 2.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 4.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.009642996825277805,
|
5 |
+
"eval_runtime": 2.6862,
|
6 |
+
"eval_samples_per_second": 30.526,
|
7 |
+
"eval_steps_per_second": 4.095
|
8 |
}
|
runs/Aug30_09-27-15_7e2de4304170/events.out.tfevents.1725010090.7e2de4304170
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ccc743383e0a22f5f70f7a6f976cbaf6b7455a920918f9fae79e94624d9319
|
3 |
+
size 40
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 2.5417372593586176e+16,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 2.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 2.5417372593586176e+16,
|
4 |
+
"train_loss": 0.15871779123942056,
|
5 |
+
"train_runtime": 30.4881,
|
6 |
+
"train_samples_per_second": 10.758,
|
7 |
+
"train_steps_per_second": 2.755
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,68 +10,68 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.47619047619047616,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 0.0001761904761904762,
|
15 |
-
"loss": 0.
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.9523809523809523,
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 0.00015238095238095237,
|
22 |
-
"loss": 0.
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.4285714285714286,
|
27 |
-
"grad_norm":
|
28 |
"learning_rate": 0.00012857142857142858,
|
29 |
-
"loss": 0.
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 1.9047619047619047,
|
34 |
-
"grad_norm": 0.
|
35 |
"learning_rate": 0.00010476190476190477,
|
36 |
-
"loss": 0.
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 2.380952380952381,
|
41 |
-
"grad_norm": 0.
|
42 |
"learning_rate": 8.095238095238096e-05,
|
43 |
-
"loss": 0.
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.857142857142857,
|
48 |
-
"grad_norm": 0.
|
49 |
"learning_rate": 5.714285714285714e-05,
|
50 |
-
"loss": 0.
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
"epoch": 3.3333333333333335,
|
55 |
-
"grad_norm": 0.
|
56 |
"learning_rate": 3.3333333333333335e-05,
|
57 |
-
"loss": 0.
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
"epoch": 3.8095238095238093,
|
62 |
-
"grad_norm": 0.
|
63 |
"learning_rate": 9.523809523809523e-06,
|
64 |
-
"loss": 0.
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
"epoch": 4.0,
|
69 |
"step": 84,
|
70 |
"total_flos": 2.5417372593586176e+16,
|
71 |
-
"train_loss": 0.
|
72 |
-
"train_runtime":
|
73 |
-
"train_samples_per_second":
|
74 |
-
"train_steps_per_second": 2.
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 10,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.47619047619047616,
|
13 |
+
"grad_norm": 2.812675952911377,
|
14 |
"learning_rate": 0.0001761904761904762,
|
15 |
+
"loss": 0.5907,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.9523809523809523,
|
20 |
+
"grad_norm": 5.478332996368408,
|
21 |
"learning_rate": 0.00015238095238095237,
|
22 |
+
"loss": 0.4214,
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 1.4285714285714286,
|
27 |
+
"grad_norm": 1.4264696836471558,
|
28 |
"learning_rate": 0.00012857142857142858,
|
29 |
+
"loss": 0.1644,
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 1.9047619047619047,
|
34 |
+
"grad_norm": 0.1871589571237564,
|
35 |
"learning_rate": 0.00010476190476190477,
|
36 |
+
"loss": 0.1012,
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 2.380952380952381,
|
41 |
+
"grad_norm": 0.10930836200714111,
|
42 |
"learning_rate": 8.095238095238096e-05,
|
43 |
+
"loss": 0.0177,
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 2.857142857142857,
|
48 |
+
"grad_norm": 0.09269272536039352,
|
49 |
"learning_rate": 5.714285714285714e-05,
|
50 |
+
"loss": 0.0132,
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
"epoch": 3.3333333333333335,
|
55 |
+
"grad_norm": 0.08020050823688507,
|
56 |
"learning_rate": 3.3333333333333335e-05,
|
57 |
+
"loss": 0.0107,
|
58 |
"step": 70
|
59 |
},
|
60 |
{
|
61 |
"epoch": 3.8095238095238093,
|
62 |
+
"grad_norm": 0.08233410120010376,
|
63 |
"learning_rate": 9.523809523809523e-06,
|
64 |
+
"loss": 0.0098,
|
65 |
"step": 80
|
66 |
},
|
67 |
{
|
68 |
"epoch": 4.0,
|
69 |
"step": 84,
|
70 |
"total_flos": 2.5417372593586176e+16,
|
71 |
+
"train_loss": 0.15871779123942056,
|
72 |
+
"train_runtime": 30.4881,
|
73 |
+
"train_samples_per_second": 10.758,
|
74 |
+
"train_steps_per_second": 2.755
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 10,
|