End of training
Browse files- README.md +1 -1
- all_results.json +8 -8
- eval_results.json +4 -4
- runs/Apr23_14-17-42_31541765f4b7/events.out.tfevents.1713882471.31541765f4b7.34.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +50 -50
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0062
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 8.42,
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime": 2.
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 1.
|
7 |
"total_flos": 7.88469671840514e+17,
|
8 |
-
"train_loss": 0.
|
9 |
-
"train_runtime":
|
10 |
-
"train_samples_per_second":
|
11 |
-
"train_steps_per_second": 0.
|
12 |
}
|
|
|
1 |
{
|
2 |
"epoch": 8.42,
|
3 |
+
"eval_loss": 0.006183081306517124,
|
4 |
+
"eval_runtime": 2.9022,
|
5 |
+
"eval_samples_per_second": 45.828,
|
6 |
+
"eval_steps_per_second": 1.034,
|
7 |
"total_flos": 7.88469671840514e+17,
|
8 |
+
"train_loss": 0.14818734787404536,
|
9 |
+
"train_runtime": 550.7447,
|
10 |
+
"train_samples_per_second": 21.68,
|
11 |
+
"train_steps_per_second": 0.073
|
12 |
}
|
eval_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 8.42,
|
3 |
-
"eval_loss": 0.
|
4 |
-
"eval_runtime": 2.
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second": 1.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 8.42,
|
3 |
+
"eval_loss": 0.006183081306517124,
|
4 |
+
"eval_runtime": 2.9022,
|
5 |
+
"eval_samples_per_second": 45.828,
|
6 |
+
"eval_steps_per_second": 1.034
|
7 |
}
|
runs/Apr23_14-17-42_31541765f4b7/events.out.tfevents.1713882471.31541765f4b7.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c8c0e2e7c6a140c2c1688fe32b05ce4012ac6d2a1ad08c77b236c8eb981385c
|
3 |
+
size 354
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 8.42,
|
3 |
"total_flos": 7.88469671840514e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 8.42,
|
3 |
"total_flos": 7.88469671840514e+17,
|
4 |
+
"train_loss": 0.14818734787404536,
|
5 |
+
"train_runtime": 550.7447,
|
6 |
+
"train_samples_per_second": 21.68,
|
7 |
+
"train_steps_per_second": 0.073
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-Kontur-competition-1.4K/checkpoint-
|
4 |
"epoch": 8.421052631578947,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 40,
|
@@ -10,112 +10,112 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.84,
|
13 |
-
"eval_loss": 0.
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 0.
|
17 |
"step": 4
|
18 |
},
|
19 |
{
|
20 |
"epoch": 1.89,
|
21 |
-
"eval_loss": 0.
|
22 |
-
"eval_runtime":
|
23 |
-
"eval_samples_per_second":
|
24 |
-
"eval_steps_per_second":
|
25 |
"step": 9
|
26 |
},
|
27 |
{
|
28 |
"epoch": 2.11,
|
29 |
-
"grad_norm":
|
30 |
"learning_rate": 4.166666666666667e-05,
|
31 |
-
"loss": 0.
|
32 |
"step": 10
|
33 |
},
|
34 |
{
|
35 |
"epoch": 2.95,
|
36 |
-
"eval_loss": 0.
|
37 |
-
"eval_runtime": 2.
|
38 |
-
"eval_samples_per_second":
|
39 |
-
"eval_steps_per_second": 1.
|
40 |
"step": 14
|
41 |
},
|
42 |
{
|
43 |
"epoch": 4.0,
|
44 |
-
"eval_loss": 0.
|
45 |
-
"eval_runtime": 2.
|
46 |
-
"eval_samples_per_second":
|
47 |
-
"eval_steps_per_second": 1.
|
48 |
"step": 19
|
49 |
},
|
50 |
{
|
51 |
"epoch": 4.21,
|
52 |
-
"grad_norm":
|
53 |
"learning_rate": 2.777777777777778e-05,
|
54 |
-
"loss": 0.
|
55 |
"step": 20
|
56 |
},
|
57 |
{
|
58 |
"epoch": 4.84,
|
59 |
-
"eval_loss": 0.
|
60 |
-
"eval_runtime": 2.
|
61 |
-
"eval_samples_per_second":
|
62 |
-
"eval_steps_per_second": 1.
|
63 |
"step": 23
|
64 |
},
|
65 |
{
|
66 |
"epoch": 5.89,
|
67 |
-
"eval_loss": 0.
|
68 |
-
"eval_runtime":
|
69 |
-
"eval_samples_per_second":
|
70 |
-
"eval_steps_per_second":
|
71 |
"step": 28
|
72 |
},
|
73 |
{
|
74 |
"epoch": 6.32,
|
75 |
-
"grad_norm":
|
76 |
"learning_rate": 1.388888888888889e-05,
|
77 |
-
"loss": 0.
|
78 |
"step": 30
|
79 |
},
|
80 |
{
|
81 |
"epoch": 6.95,
|
82 |
-
"eval_loss": 0.
|
83 |
-
"eval_runtime": 2.
|
84 |
-
"eval_samples_per_second":
|
85 |
-
"eval_steps_per_second": 1.
|
86 |
"step": 33
|
87 |
},
|
88 |
{
|
89 |
"epoch": 8.0,
|
90 |
-
"eval_loss": 0.
|
91 |
-
"eval_runtime": 2.
|
92 |
-
"eval_samples_per_second":
|
93 |
-
"eval_steps_per_second": 1.
|
94 |
"step": 38
|
95 |
},
|
96 |
{
|
97 |
"epoch": 8.42,
|
98 |
-
"grad_norm":
|
99 |
"learning_rate": 0.0,
|
100 |
-
"loss": 0.
|
101 |
"step": 40
|
102 |
},
|
103 |
{
|
104 |
"epoch": 8.42,
|
105 |
-
"eval_loss": 0.
|
106 |
-
"eval_runtime": 2.
|
107 |
-
"eval_samples_per_second":
|
108 |
-
"eval_steps_per_second": 1.
|
109 |
"step": 40
|
110 |
},
|
111 |
{
|
112 |
"epoch": 8.42,
|
113 |
"step": 40,
|
114 |
"total_flos": 7.88469671840514e+17,
|
115 |
-
"train_loss": 0.
|
116 |
-
"train_runtime":
|
117 |
-
"train_samples_per_second":
|
118 |
-
"train_steps_per_second": 0.
|
119 |
}
|
120 |
],
|
121 |
"logging_steps": 10,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.006183081306517124,
|
3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-Kontur-competition-1.4K/checkpoint-19",
|
4 |
"epoch": 8.421052631578947,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 40,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.84,
|
13 |
+
"eval_loss": 0.5152684450149536,
|
14 |
+
"eval_runtime": 5.7612,
|
15 |
+
"eval_samples_per_second": 23.086,
|
16 |
+
"eval_steps_per_second": 0.521,
|
17 |
"step": 4
|
18 |
},
|
19 |
{
|
20 |
"epoch": 1.89,
|
21 |
+
"eval_loss": 0.14250300824642181,
|
22 |
+
"eval_runtime": 3.5004,
|
23 |
+
"eval_samples_per_second": 37.995,
|
24 |
+
"eval_steps_per_second": 0.857,
|
25 |
"step": 9
|
26 |
},
|
27 |
{
|
28 |
"epoch": 2.11,
|
29 |
+
"grad_norm": 2.0780093669891357,
|
30 |
"learning_rate": 4.166666666666667e-05,
|
31 |
+
"loss": 0.4963,
|
32 |
"step": 10
|
33 |
},
|
34 |
{
|
35 |
"epoch": 2.95,
|
36 |
+
"eval_loss": 0.03258229419589043,
|
37 |
+
"eval_runtime": 2.856,
|
38 |
+
"eval_samples_per_second": 46.569,
|
39 |
+
"eval_steps_per_second": 1.05,
|
40 |
"step": 14
|
41 |
},
|
42 |
{
|
43 |
"epoch": 4.0,
|
44 |
+
"eval_loss": 0.006183081306517124,
|
45 |
+
"eval_runtime": 2.8656,
|
46 |
+
"eval_samples_per_second": 46.412,
|
47 |
+
"eval_steps_per_second": 1.047,
|
48 |
"step": 19
|
49 |
},
|
50 |
{
|
51 |
"epoch": 4.21,
|
52 |
+
"grad_norm": 4.404883861541748,
|
53 |
"learning_rate": 2.777777777777778e-05,
|
54 |
+
"loss": 0.0546,
|
55 |
"step": 20
|
56 |
},
|
57 |
{
|
58 |
"epoch": 4.84,
|
59 |
+
"eval_loss": 0.11129578948020935,
|
60 |
+
"eval_runtime": 2.942,
|
61 |
+
"eval_samples_per_second": 45.207,
|
62 |
+
"eval_steps_per_second": 1.02,
|
63 |
"step": 23
|
64 |
},
|
65 |
{
|
66 |
"epoch": 5.89,
|
67 |
+
"eval_loss": 0.019418848678469658,
|
68 |
+
"eval_runtime": 3.0717,
|
69 |
+
"eval_samples_per_second": 43.299,
|
70 |
+
"eval_steps_per_second": 0.977,
|
71 |
"step": 28
|
72 |
},
|
73 |
{
|
74 |
"epoch": 6.32,
|
75 |
+
"grad_norm": 4.566842079162598,
|
76 |
"learning_rate": 1.388888888888889e-05,
|
77 |
+
"loss": 0.0216,
|
78 |
"step": 30
|
79 |
},
|
80 |
{
|
81 |
"epoch": 6.95,
|
82 |
+
"eval_loss": 0.006876213010400534,
|
83 |
+
"eval_runtime": 2.9022,
|
84 |
+
"eval_samples_per_second": 45.828,
|
85 |
+
"eval_steps_per_second": 1.034,
|
86 |
"step": 33
|
87 |
},
|
88 |
{
|
89 |
"epoch": 8.0,
|
90 |
+
"eval_loss": 0.009907796047627926,
|
91 |
+
"eval_runtime": 2.917,
|
92 |
+
"eval_samples_per_second": 45.594,
|
93 |
+
"eval_steps_per_second": 1.028,
|
94 |
"step": 38
|
95 |
},
|
96 |
{
|
97 |
"epoch": 8.42,
|
98 |
+
"grad_norm": 2.6469647884368896,
|
99 |
"learning_rate": 0.0,
|
100 |
+
"loss": 0.0203,
|
101 |
"step": 40
|
102 |
},
|
103 |
{
|
104 |
"epoch": 8.42,
|
105 |
+
"eval_loss": 0.012587403878569603,
|
106 |
+
"eval_runtime": 2.9395,
|
107 |
+
"eval_samples_per_second": 45.246,
|
108 |
+
"eval_steps_per_second": 1.021,
|
109 |
"step": 40
|
110 |
},
|
111 |
{
|
112 |
"epoch": 8.42,
|
113 |
"step": 40,
|
114 |
"total_flos": 7.88469671840514e+17,
|
115 |
+
"train_loss": 0.14818734787404536,
|
116 |
+
"train_runtime": 550.7447,
|
117 |
+
"train_samples_per_second": 21.68,
|
118 |
+
"train_steps_per_second": 0.073
|
119 |
}
|
120 |
],
|
121 |
"logging_steps": 10,
|