Hugging Face's logo

cafeai
/
cafe_style

Image Classification
Transformers
PyTorch
beit
Inference Endpoints
Model card Files Community
1
cafeai commited on
Commit
de57fdb
•
1 Parent(s): d1d9b3e

v2

Browse files
Files changed (5) hide show
  1. all_results.json +5 -5
  2. pytorch_model.bin +1 -1
  3. train_results.json +5 -5
  4. trainer_state.json +167 -20
  5. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 2.0,
3
- "train_loss": 0.8248079419136047,
4
- "train_runtime": 281.7391,
5
- "train_samples_per_second": 21.68,
6
- "train_steps_per_second": 0.057
7
  }
 
1
  {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.5977009888738394,
4
+ "train_runtime": 725.9122,
5
+ "train_samples_per_second": 16.828,
6
+ "train_steps_per_second": 0.044
7
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d9c3f997a25564b765e20f4b7de04c917c415843302e71ed8acd2a8b42cdea8
3
  size 375957689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c54847c4cc7b892017219bf5ba06a6214ad38a8b75a60733e37033c94a922a14
3
  size 375957689
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 2.0,
3
- "train_loss": 0.8248079419136047,
4
- "train_runtime": 281.7391,
5
- "train_samples_per_second": 21.68,
6
- "train_steps_per_second": 0.057
7
  }
 
1
  {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.5977009888738394,
4
+ "train_runtime": 725.9122,
5
+ "train_samples_per_second": 16.828,
6
+ "train_steps_per_second": 0.044
7
  }
trainer_state.json CHANGED
@@ -1,40 +1,187 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.0,
5
- "global_step": 16,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  {
11
  "epoch": 1.25,
12
- "learning_rate": 2.1428571428571428e-05,
13
- "loss": 1.0133,
14
  "step": 10
15
  },
16
  {
17
  "epoch": 1.25,
18
- "eval_accuracy": 0.8441176470588235,
19
- "eval_loss": 0.5216343998908997,
20
- "eval_runtime": 11.8985,
21
- "eval_samples_per_second": 28.575,
22
- "eval_steps_per_second": 0.168,
23
  "step": 10
24
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  {
26
  "epoch": 2.0,
27
- "step": 16,
28
- "total_flos": 1.3938823351452303e+18,
29
- "train_loss": 0.8248079419136047,
30
- "train_runtime": 281.7391,
31
- "train_samples_per_second": 21.68,
32
- "train_steps_per_second": 0.057
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
- "max_steps": 16,
36
- "num_train_epochs": 2,
37
- "total_flos": 1.3938823351452303e+18,
38
  "trial_name": null,
39
  "trial_params": null
40
  }
 
1
  {
2
+ "best_metric": 0.8735294117647059,
3
+ "best_model_checkpoint": "beit-base-patch16-384-finetuned-style-cafe/checkpoint-30",
4
+ "epoch": 4.0,
5
+ "global_step": 32,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
+ {
11
+ "epoch": 0.25,
12
+ "eval_accuracy": 0.5764705882352941,
13
+ "eval_loss": 1.2258567810058594,
14
+ "eval_runtime": 10.8099,
15
+ "eval_samples_per_second": 31.453,
16
+ "eval_steps_per_second": 0.185,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.5,
21
+ "eval_accuracy": 0.6852941176470588,
22
+ "eval_loss": 0.8997119069099426,
23
+ "eval_runtime": 10.9229,
24
+ "eval_samples_per_second": 31.127,
25
+ "eval_steps_per_second": 0.183,
26
+ "step": 4
27
+ },
28
+ {
29
+ "epoch": 0.75,
30
+ "eval_accuracy": 0.7735294117647059,
31
+ "eval_loss": 0.6791498064994812,
32
+ "eval_runtime": 10.7919,
33
+ "eval_samples_per_second": 31.505,
34
+ "eval_steps_per_second": 0.185,
35
+ "step": 6
36
+ },
37
+ {
38
+ "epoch": 1.0,
39
+ "eval_accuracy": 0.8441176470588235,
40
+ "eval_loss": 0.5481722950935364,
41
+ "eval_runtime": 10.7067,
42
+ "eval_samples_per_second": 31.756,
43
+ "eval_steps_per_second": 0.187,
44
+ "step": 8
45
+ },
46
  {
47
  "epoch": 1.25,
48
+ "learning_rate": 3.928571428571429e-05,
49
+ "loss": 1.0539,
50
  "step": 10
51
  },
52
  {
53
  "epoch": 1.25,
54
+ "eval_accuracy": 0.8588235294117647,
55
+ "eval_loss": 0.46222972869873047,
56
+ "eval_runtime": 10.7269,
57
+ "eval_samples_per_second": 31.696,
58
+ "eval_steps_per_second": 0.186,
59
  "step": 10
60
  },
61
+ {
62
+ "epoch": 1.5,
63
+ "eval_accuracy": 0.8529411764705882,
64
+ "eval_loss": 0.43965184688568115,
65
+ "eval_runtime": 10.7273,
66
+ "eval_samples_per_second": 31.695,
67
+ "eval_steps_per_second": 0.186,
68
+ "step": 12
69
+ },
70
+ {
71
+ "epoch": 1.75,
72
+ "eval_accuracy": 0.8441176470588235,
73
+ "eval_loss": 0.41807717084884644,
74
+ "eval_runtime": 10.7319,
75
+ "eval_samples_per_second": 31.681,
76
+ "eval_steps_per_second": 0.186,
77
+ "step": 14
78
+ },
79
  {
80
  "epoch": 2.0,
81
+ "eval_accuracy": 0.8470588235294118,
82
+ "eval_loss": 0.38893890380859375,
83
+ "eval_runtime": 10.6958,
84
+ "eval_samples_per_second": 31.788,
85
+ "eval_steps_per_second": 0.187,
86
+ "step": 16
87
+ },
88
+ {
89
+ "epoch": 2.25,
90
+ "eval_accuracy": 0.8588235294117647,
91
+ "eval_loss": 0.3727969527244568,
92
+ "eval_runtime": 10.7111,
93
+ "eval_samples_per_second": 31.743,
94
+ "eval_steps_per_second": 0.187,
95
+ "step": 18
96
+ },
97
+ {
98
+ "epoch": 2.5,
99
+ "learning_rate": 2.1428571428571428e-05,
100
+ "loss": 0.4523,
101
+ "step": 20
102
+ },
103
+ {
104
+ "epoch": 2.5,
105
+ "eval_accuracy": 0.8588235294117647,
106
+ "eval_loss": 0.3681255578994751,
107
+ "eval_runtime": 10.6816,
108
+ "eval_samples_per_second": 31.83,
109
+ "eval_steps_per_second": 0.187,
110
+ "step": 20
111
+ },
112
+ {
113
+ "epoch": 2.75,
114
+ "eval_accuracy": 0.8676470588235294,
115
+ "eval_loss": 0.3621581792831421,
116
+ "eval_runtime": 10.7596,
117
+ "eval_samples_per_second": 31.6,
118
+ "eval_steps_per_second": 0.186,
119
+ "step": 22
120
+ },
121
+ {
122
+ "epoch": 3.0,
123
+ "eval_accuracy": 0.8676470588235294,
124
+ "eval_loss": 0.36003121733665466,
125
+ "eval_runtime": 10.933,
126
+ "eval_samples_per_second": 31.098,
127
+ "eval_steps_per_second": 0.183,
128
+ "step": 24
129
+ },
130
+ {
131
+ "epoch": 3.25,
132
+ "eval_accuracy": 0.8647058823529412,
133
+ "eval_loss": 0.3558030426502228,
134
+ "eval_runtime": 10.6994,
135
+ "eval_samples_per_second": 31.777,
136
+ "eval_steps_per_second": 0.187,
137
+ "step": 26
138
+ },
139
+ {
140
+ "epoch": 3.5,
141
+ "eval_accuracy": 0.8676470588235294,
142
+ "eval_loss": 0.34111377596855164,
143
+ "eval_runtime": 10.7517,
144
+ "eval_samples_per_second": 31.623,
145
+ "eval_steps_per_second": 0.186,
146
+ "step": 28
147
+ },
148
+ {
149
+ "epoch": 3.75,
150
+ "learning_rate": 3.5714285714285714e-06,
151
+ "loss": 0.3439,
152
+ "step": 30
153
+ },
154
+ {
155
+ "epoch": 3.75,
156
+ "eval_accuracy": 0.8735294117647059,
157
+ "eval_loss": 0.33768245577812195,
158
+ "eval_runtime": 10.7509,
159
+ "eval_samples_per_second": 31.625,
160
+ "eval_steps_per_second": 0.186,
161
+ "step": 30
162
+ },
163
+ {
164
+ "epoch": 4.0,
165
+ "eval_accuracy": 0.8735294117647059,
166
+ "eval_loss": 0.33675017952919006,
167
+ "eval_runtime": 10.835,
168
+ "eval_samples_per_second": 31.38,
169
+ "eval_steps_per_second": 0.185,
170
+ "step": 32
171
+ },
172
+ {
173
+ "epoch": 4.0,
174
+ "step": 32,
175
+ "total_flos": 2.7877646702904607e+18,
176
+ "train_loss": 0.5977009888738394,
177
+ "train_runtime": 725.9122,
178
+ "train_samples_per_second": 16.828,
179
+ "train_steps_per_second": 0.044
180
  }
181
  ],
182
+ "max_steps": 32,
183
+ "num_train_epochs": 4,
184
+ "total_flos": 2.7877646702904607e+18,
185
  "trial_name": null,
186
  "trial_params": null
187
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceda96102eba37372eb83808fcfad17e440f04f070f6433850e7c46544ad65fc
3
  size 3387
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:927e3eadcdd575149b0bb5416167fac405d9bc33b965e45a809c6ebf3da3d30a
3
  size 3387