Hugging Face's logo

ogimgio
/
vit-base-highways-2

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ogimgio commited on
Commit
4d86804
•
1 Parent(s): f090513

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +106 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 7.7491989614592e+16,
4
+ "train_loss": 0.09034528125018354,
5
+ "train_runtime": 299.6231,
6
+ "train_samples_per_second": 3.338,
7
+ "train_steps_per_second": 0.421
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 7.7491989614592e+16,
4
+ "train_loss": 0.09034528125018354,
5
+ "train_runtime": 299.6231,
6
+ "train_samples_per_second": 3.338,
7
+ "train_steps_per_second": 0.421
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.21961037814617157,
3
+ "best_model_checkpoint": "./vit-base-highways-2/checkpoint-100",
4
+ "epoch": 2.0,
5
+ "global_step": 126,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 0.00018412698412698412,
13
+ "loss": 0.0048,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.32,
18
+ "learning_rate": 0.00016825396825396826,
19
+ "loss": 0.0016,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.48,
24
+ "learning_rate": 0.00015238095238095237,
25
+ "loss": 0.1014,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.63,
30
+ "learning_rate": 0.0001365079365079365,
31
+ "loss": 0.2578,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.79,
36
+ "learning_rate": 0.00012063492063492063,
37
+ "loss": 0.4379,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.95,
42
+ "learning_rate": 0.00010476190476190477,
43
+ "loss": 0.2386,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 1.11,
48
+ "learning_rate": 8.888888888888889e-05,
49
+ "loss": 0.0062,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 1.27,
54
+ "learning_rate": 7.301587301587302e-05,
55
+ "loss": 0.0102,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 1.43,
60
+ "learning_rate": 5.714285714285714e-05,
61
+ "loss": 0.0596,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 1.59,
66
+ "learning_rate": 4.126984126984127e-05,
67
+ "loss": 0.0012,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 1.59,
72
+ "eval_accuracy": 0.96,
73
+ "eval_loss": 0.21961037814617157,
74
+ "eval_runtime": 32.5474,
75
+ "eval_samples_per_second": 3.841,
76
+ "eval_steps_per_second": 0.492,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 1.75,
81
+ "learning_rate": 2.5396825396825397e-05,
82
+ "loss": 0.001,
83
+ "step": 110
84
+ },
85
+ {
86
+ "epoch": 1.9,
87
+ "learning_rate": 9.523809523809523e-06,
88
+ "loss": 0.0175,
89
+ "step": 120
90
+ },
91
+ {
92
+ "epoch": 2.0,
93
+ "step": 126,
94
+ "total_flos": 7.7491989614592e+16,
95
+ "train_loss": 0.09034528125018354,
96
+ "train_runtime": 299.6231,
97
+ "train_samples_per_second": 3.338,
98
+ "train_steps_per_second": 0.421
99
+ }
100
+ ],
101
+ "max_steps": 126,
102
+ "num_train_epochs": 2,
103
+ "total_flos": 7.7491989614592e+16,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }