johnnydevriese commited on
Commit
7208ffe
1 Parent(s): ef3a41d
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.015230490826070309,
5
+ "eval_runtime": 58.1774,
6
+ "eval_samples_per_second": 11.465,
7
+ "eval_steps_per_second": 1.444,
8
+ "total_flos": 2.067504813142917e+17,
9
+ "train_loss": 0.04814572525875909,
10
+ "train_runtime": 540.2683,
11
+ "train_samples_per_second": 4.938,
12
+ "train_steps_per_second": 0.311
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.015230490826070309,
5
+ "eval_runtime": 58.1774,
6
+ "eval_samples_per_second": 11.465,
7
+ "eval_steps_per_second": 1.444
8
+ }
runs/Apr08_16-44-55_e98349974501/events.out.tfevents.1649437374.e98349974501.72.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690e341e3bbed9b9512ae936c8d44fdb45c985e691b92e032979e7370a4cea17
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 2.067504813142917e+17,
4
+ "train_loss": 0.04814572525875909,
5
+ "train_runtime": 540.2683,
6
+ "train_samples_per_second": 4.938,
7
+ "train_steps_per_second": 0.311
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.015230490826070309,
3
+ "best_model_checkpoint": "./vit-airplanes/checkpoint-100",
4
+ "epoch": 4.0,
5
+ "global_step": 168,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.24,
12
+ "learning_rate": 0.0001880952380952381,
13
+ "loss": 0.3543,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.48,
18
+ "learning_rate": 0.0001761904761904762,
19
+ "loss": 0.1221,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.71,
24
+ "learning_rate": 0.00016428571428571428,
25
+ "loss": 0.0587,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.95,
30
+ "learning_rate": 0.00015238095238095237,
31
+ "loss": 0.0441,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 1.19,
36
+ "learning_rate": 0.00014047619047619049,
37
+ "loss": 0.0281,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 1.43,
42
+ "learning_rate": 0.00012857142857142858,
43
+ "loss": 0.0302,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 1.67,
48
+ "learning_rate": 0.00011666666666666668,
49
+ "loss": 0.0417,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 1.9,
54
+ "learning_rate": 0.00010476190476190477,
55
+ "loss": 0.0192,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 2.14,
60
+ "learning_rate": 9.285714285714286e-05,
61
+ "loss": 0.0129,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 2.38,
66
+ "learning_rate": 8.095238095238096e-05,
67
+ "loss": 0.0165,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 2.38,
72
+ "eval_accuracy": 1.0,
73
+ "eval_loss": 0.015230490826070309,
74
+ "eval_runtime": 56.286,
75
+ "eval_samples_per_second": 11.85,
76
+ "eval_steps_per_second": 1.492,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 2.62,
81
+ "learning_rate": 6.904761904761905e-05,
82
+ "loss": 0.0184,
83
+ "step": 110
84
+ },
85
+ {
86
+ "epoch": 2.86,
87
+ "learning_rate": 5.714285714285714e-05,
88
+ "loss": 0.0117,
89
+ "step": 120
90
+ },
91
+ {
92
+ "epoch": 3.1,
93
+ "learning_rate": 4.523809523809524e-05,
94
+ "loss": 0.0128,
95
+ "step": 130
96
+ },
97
+ {
98
+ "epoch": 3.33,
99
+ "learning_rate": 3.3333333333333335e-05,
100
+ "loss": 0.0132,
101
+ "step": 140
102
+ },
103
+ {
104
+ "epoch": 3.57,
105
+ "learning_rate": 2.1428571428571428e-05,
106
+ "loss": 0.0099,
107
+ "step": 150
108
+ },
109
+ {
110
+ "epoch": 3.81,
111
+ "learning_rate": 9.523809523809523e-06,
112
+ "loss": 0.0082,
113
+ "step": 160
114
+ },
115
+ {
116
+ "epoch": 4.0,
117
+ "step": 168,
118
+ "total_flos": 2.067504813142917e+17,
119
+ "train_loss": 0.04814572525875909,
120
+ "train_runtime": 540.2683,
121
+ "train_samples_per_second": 4.938,
122
+ "train_steps_per_second": 0.311
123
+ }
124
+ ],
125
+ "max_steps": 168,
126
+ "num_train_epochs": 4,
127
+ "total_flos": 2.067504813142917e+17,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }