Hugging Face's logo

gary2002
/
output_dir-full_dataset

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
 Metrics Community
gary2002 commited on
Commit
427b7ba
·
verified ·
1 Parent(s): 1bf8c6f

./google-vit-base-patch16-224-in21k-9H

Browse files
Files changed (5) hide show
  1. all_results.json +13 -0
  2. eval_results.json +8 -0
  3. runs/Mar21_05-30-31_91386b7835d7/events.out.tfevents.1711003565.91386b7835d7.1965.2 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +176 -0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9169753086419753,
4
+ "eval_loss": 0.20968997478485107,
5
+ "eval_runtime": 111.5277,
6
+ "eval_samples_per_second": 29.051,
7
+ "eval_steps_per_second": 7.263,
8
+ "total_flos": 6.779424557667041e+18,
9
+ "train_loss": 1.086526616065536,
10
+ "train_runtime": 4256.354,
11
+ "train_samples_per_second": 20.553,
12
+ "train_steps_per_second": 2.055
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9169753086419753,
4
+ "eval_loss": 0.20968997478485107,
5
+ "eval_runtime": 111.5277,
6
+ "eval_samples_per_second": 29.051,
7
+ "eval_steps_per_second": 7.263
8
+ }
runs/Mar21_05-30-31_91386b7835d7/events.out.tfevents.1711003565.91386b7835d7.1965.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9024a7e0724883b134089554401537f995e81124b347a55ae3ed069035af7750
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 6.779424557667041e+18,
4
+ "train_loss": 1.086526616065536,
5
+ "train_runtime": 4256.354,
6
+ "train_samples_per_second": 20.553,
7
+ "train_steps_per_second": 2.055
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9169753086419753,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/graduate_design/ViT_train_pictures/output_dir-full_dataset/checkpoint-8748",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 8748,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.17,
13
+ "grad_norm": 0.8087803721427917,
14
+ "learning_rate": 0.00018856881572930955,
15
+ "loss": 2.2007,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.34,
20
+ "grad_norm": 0.5222867131233215,
21
+ "learning_rate": 0.00017716049382716052,
22
+ "loss": 2.2033,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.51,
27
+ "grad_norm": 0.728941023349762,
28
+ "learning_rate": 0.00016572930955647007,
29
+ "loss": 2.1961,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.69,
34
+ "grad_norm": 0.4614827632904053,
35
+ "learning_rate": 0.0001542981252857796,
36
+ "loss": 2.198,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.86,
41
+ "grad_norm": 0.6945221424102783,
42
+ "learning_rate": 0.00014286694101508919,
43
+ "loss": 2.1689,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "eval_accuracy": 0.3398148148148148,
49
+ "eval_loss": 1.592108130455017,
50
+ "eval_runtime": 114.0279,
51
+ "eval_samples_per_second": 28.414,
52
+ "eval_steps_per_second": 7.104,
53
+ "step": 2916
54
+ },
55
+ {
56
+ "epoch": 1.03,
57
+ "grad_norm": 2.6183340549468994,
58
+ "learning_rate": 0.0001314586191129401,
59
+ "loss": 1.7575,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 1.2,
64
+ "grad_norm": 3.532482147216797,
65
+ "learning_rate": 0.00012002743484224966,
66
+ "loss": 1.2952,
67
+ "step": 3500
68
+ },
69
+ {
70
+ "epoch": 1.37,
71
+ "grad_norm": 3.6780481338500977,
72
+ "learning_rate": 0.00010859625057155922,
73
+ "loss": 1.0195,
74
+ "step": 4000
75
+ },
76
+ {
77
+ "epoch": 1.54,
78
+ "grad_norm": 5.143928050994873,
79
+ "learning_rate": 9.716506630086878e-05,
80
+ "loss": 0.7956,
81
+ "step": 4500
82
+ },
83
+ {
84
+ "epoch": 1.71,
85
+ "grad_norm": 10.191193580627441,
86
+ "learning_rate": 8.575674439871972e-05,
87
+ "loss": 0.6654,
88
+ "step": 5000
89
+ },
90
+ {
91
+ "epoch": 1.89,
92
+ "grad_norm": 6.73974609375,
93
+ "learning_rate": 7.432556012802928e-05,
94
+ "loss": 0.5282,
95
+ "step": 5500
96
+ },
97
+ {
98
+ "epoch": 2.0,
99
+ "eval_accuracy": 0.8296296296296296,
100
+ "eval_loss": 0.4584006369113922,
101
+ "eval_runtime": 108.7745,
102
+ "eval_samples_per_second": 29.786,
103
+ "eval_steps_per_second": 7.447,
104
+ "step": 5832
105
+ },
106
+ {
107
+ "epoch": 2.06,
108
+ "grad_norm": 6.977649211883545,
109
+ "learning_rate": 6.294010059442158e-05,
110
+ "loss": 0.4526,
111
+ "step": 6000
112
+ },
113
+ {
114
+ "epoch": 2.23,
115
+ "grad_norm": 6.755834579467773,
116
+ "learning_rate": 5.1508916323731135e-05,
117
+ "loss": 0.3721,
118
+ "step": 6500
119
+ },
120
+ {
121
+ "epoch": 2.4,
122
+ "grad_norm": 1.0103096961975098,
123
+ "learning_rate": 4.007773205304069e-05,
124
+ "loss": 0.3228,
125
+ "step": 7000
126
+ },
127
+ {
128
+ "epoch": 2.57,
129
+ "grad_norm": 0.03946676105260849,
130
+ "learning_rate": 2.864654778235025e-05,
131
+ "loss": 0.28,
132
+ "step": 7500
133
+ },
134
+ {
135
+ "epoch": 2.74,
136
+ "grad_norm": 0.23168502748012543,
137
+ "learning_rate": 1.721536351165981e-05,
138
+ "loss": 0.2356,
139
+ "step": 8000
140
+ },
141
+ {
142
+ "epoch": 2.91,
143
+ "grad_norm": 4.113630771636963,
144
+ "learning_rate": 5.807041609510746e-06,
145
+ "loss": 0.2224,
146
+ "step": 8500
147
+ },
148
+ {
149
+ "epoch": 3.0,
150
+ "eval_accuracy": 0.9169753086419753,
151
+ "eval_loss": 0.20968997478485107,
152
+ "eval_runtime": 114.304,
153
+ "eval_samples_per_second": 28.345,
154
+ "eval_steps_per_second": 7.086,
155
+ "step": 8748
156
+ },
157
+ {
158
+ "epoch": 3.0,
159
+ "step": 8748,
160
+ "total_flos": 6.779424557667041e+18,
161
+ "train_loss": 1.086526616065536,
162
+ "train_runtime": 4256.354,
163
+ "train_samples_per_second": 20.553,
164
+ "train_steps_per_second": 2.055
165
+ }
166
+ ],
167
+ "logging_steps": 500,
168
+ "max_steps": 8748,
169
+ "num_input_tokens_seen": 0,
170
+ "num_train_epochs": 3,
171
+ "save_steps": 500,
172
+ "total_flos": 6.779424557667041e+18,
173
+ "train_batch_size": 10,
174
+ "trial_name": null,
175
+ "trial_params": null
176
+ }