Hugging Face's logo

rshrott
/
vit-base-renovation

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
rshrott commited on
Commit
86e3a80
•
1 Parent(s): da03fe3

🍻 cheers

Browse files
Files changed (5) hide show
  1. all_results.json +10 -10
  2. eval_results.json +5 -5
  3. runs/Jul18_22-42-09_7f33c8735581/events.out.tfevents.1689720638.7f33c8735581.12947.1 +3 -0
  4. train_results.json +5 -5
  5. trainer_state.json +167 -17
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 4.0,
3
- "eval_accuracy": 0.5,
4
- "eval_loss": 0.977874755859375,
5
- "eval_runtime": 0.7061,
6
- "eval_samples_per_second": 14.162,
7
- "eval_steps_per_second": 2.832,
8
- "total_flos": 2.479765892825088e+16,
9
- "train_loss": 0.2677663803100586,
10
- "train_runtime": 23.2011,
11
- "train_samples_per_second": 13.792,
12
- "train_steps_per_second": 0.862
13
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "eval_accuracy": 0.9,
4
+ "eval_loss": 0.5519602298736572,
5
+ "eval_runtime": 2.1697,
6
+ "eval_samples_per_second": 13.827,
7
+ "eval_steps_per_second": 1.844,
8
+ "total_flos": 2.972619364024074e+17,
9
+ "train_loss": 0.5838068192203839,
10
+ "train_runtime": 384.6439,
11
+ "train_samples_per_second": 9.973,
12
+ "train_steps_per_second": 0.624
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
- "eval_accuracy": 0.5,
4
- "eval_loss": 0.977874755859375,
5
- "eval_runtime": 0.7061,
6
- "eval_samples_per_second": 14.162,
7
- "eval_steps_per_second": 2.832
8
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "eval_accuracy": 0.9,
4
+ "eval_loss": 0.5519602298736572,
5
+ "eval_runtime": 2.1697,
6
+ "eval_samples_per_second": 13.827,
7
+ "eval_steps_per_second": 1.844
8
  }
runs/Jul18_22-42-09_7f33c8735581/events.out.tfevents.1689720638.7f33c8735581.12947.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6805bc24f3c2bc030e88ff20949ccac5b7f814b37b5b08b492cf7ebab431177e
3
+ size 411
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
- "total_flos": 2.479765892825088e+16,
4
- "train_loss": 0.2677663803100586,
5
- "train_runtime": 23.2011,
6
- "train_samples_per_second": 13.792,
7
- "train_steps_per_second": 0.862
8
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "total_flos": 2.972619364024074e+17,
4
+ "train_loss": 0.5838068192203839,
5
+ "train_runtime": 384.6439,
6
+ "train_samples_per_second": 9.973,
7
+ "train_steps_per_second": 0.624
8
  }
trainer_state.json CHANGED
@@ -1,37 +1,187 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
  "epoch": 4.0,
5
- "global_step": 20,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 2.0,
12
- "learning_rate": 0.0001,
13
- "loss": 0.3999,
14
  "step": 10
15
  },
16
  {
17
- "epoch": 4.0,
18
- "learning_rate": 0.0,
19
- "loss": 0.1356,
20
  "step": 20
21
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  {
23
  "epoch": 4.0,
24
- "step": 20,
25
- "total_flos": 2.479765892825088e+16,
26
- "train_loss": 0.2677663803100586,
27
- "train_runtime": 23.2011,
28
- "train_samples_per_second": 13.792,
29
- "train_steps_per_second": 0.862
30
  }
31
  ],
32
- "max_steps": 20,
33
  "num_train_epochs": 4,
34
- "total_flos": 2.479765892825088e+16,
35
  "trial_name": null,
36
  "trial_params": null
37
  }
 
1
  {
2
+ "best_metric": 0.5519602298736572,
3
+ "best_model_checkpoint": "./vit-base-renovation/checkpoint-200",
4
  "epoch": 4.0,
5
+ "global_step": 240,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 0.17,
12
+ "learning_rate": 0.00019166666666666667,
13
+ "loss": 1.0207,
14
  "step": 10
15
  },
16
  {
17
+ "epoch": 0.33,
18
+ "learning_rate": 0.00018333333333333334,
19
+ "loss": 0.9553,
20
  "step": 20
21
  },
22
+ {
23
+ "epoch": 0.5,
24
+ "learning_rate": 0.000175,
25
+ "loss": 0.9262,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.67,
30
+ "learning_rate": 0.0001666666666666667,
31
+ "loss": 1.0583,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.83,
36
+ "learning_rate": 0.00015833333333333332,
37
+ "loss": 0.9631,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "learning_rate": 0.00015000000000000001,
43
+ "loss": 1.0413,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 1.17,
48
+ "learning_rate": 0.00014250000000000002,
49
+ "loss": 0.8439,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 1.33,
54
+ "learning_rate": 0.00013416666666666666,
55
+ "loss": 0.8593,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 1.5,
60
+ "learning_rate": 0.00012583333333333335,
61
+ "loss": 0.7704,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 1.67,
66
+ "learning_rate": 0.00011833333333333334,
67
+ "loss": 0.7677,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 1.67,
72
+ "eval_accuracy": 0.7666666666666667,
73
+ "eval_loss": 0.677022397518158,
74
+ "eval_runtime": 2.0668,
75
+ "eval_samples_per_second": 14.515,
76
+ "eval_steps_per_second": 1.935,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 1.83,
81
+ "learning_rate": 0.00011000000000000002,
82
+ "loss": 0.869,
83
+ "step": 110
84
+ },
85
+ {
86
+ "epoch": 2.0,
87
+ "learning_rate": 0.00010166666666666667,
88
+ "loss": 0.713,
89
+ "step": 120
90
+ },
91
+ {
92
+ "epoch": 2.17,
93
+ "learning_rate": 9.333333333333334e-05,
94
+ "loss": 0.516,
95
+ "step": 130
96
+ },
97
+ {
98
+ "epoch": 2.33,
99
+ "learning_rate": 8.5e-05,
100
+ "loss": 0.436,
101
+ "step": 140
102
+ },
103
+ {
104
+ "epoch": 2.5,
105
+ "learning_rate": 7.666666666666667e-05,
106
+ "loss": 0.4567,
107
+ "step": 150
108
+ },
109
+ {
110
+ "epoch": 2.67,
111
+ "learning_rate": 6.833333333333333e-05,
112
+ "loss": 0.3406,
113
+ "step": 160
114
+ },
115
+ {
116
+ "epoch": 2.83,
117
+ "learning_rate": 6e-05,
118
+ "loss": 0.3733,
119
+ "step": 170
120
+ },
121
+ {
122
+ "epoch": 3.0,
123
+ "learning_rate": 5.166666666666667e-05,
124
+ "loss": 0.3386,
125
+ "step": 180
126
+ },
127
+ {
128
+ "epoch": 3.17,
129
+ "learning_rate": 4.3333333333333334e-05,
130
+ "loss": 0.2098,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 3.33,
135
+ "learning_rate": 3.5e-05,
136
+ "loss": 0.13,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 3.33,
141
+ "eval_accuracy": 0.9,
142
+ "eval_loss": 0.5519602298736572,
143
+ "eval_runtime": 1.3933,
144
+ "eval_samples_per_second": 21.532,
145
+ "eval_steps_per_second": 2.871,
146
+ "step": 200
147
+ },
148
+ {
149
+ "epoch": 3.5,
150
+ "learning_rate": 2.6666666666666667e-05,
151
+ "loss": 0.1127,
152
+ "step": 210
153
+ },
154
+ {
155
+ "epoch": 3.67,
156
+ "learning_rate": 1.8333333333333333e-05,
157
+ "loss": 0.0929,
158
+ "step": 220
159
+ },
160
+ {
161
+ "epoch": 3.83,
162
+ "learning_rate": 1e-05,
163
+ "loss": 0.1072,
164
+ "step": 230
165
+ },
166
+ {
167
+ "epoch": 4.0,
168
+ "learning_rate": 1.6666666666666667e-06,
169
+ "loss": 0.1091,
170
+ "step": 240
171
+ },
172
  {
173
  "epoch": 4.0,
174
+ "step": 240,
175
+ "total_flos": 2.972619364024074e+17,
176
+ "train_loss": 0.5838068192203839,
177
+ "train_runtime": 384.6439,
178
+ "train_samples_per_second": 9.973,
179
+ "train_steps_per_second": 0.624
180
  }
181
  ],
182
+ "max_steps": 240,
183
  "num_train_epochs": 4,
184
+ "total_flos": 2.972619364024074e+17,
185
  "trial_name": null,
186
  "trial_params": null
187
  }