dvs commited on
Commit
7ee195f
1 Parent(s): bbe2235

End of training

Browse files
all_results.json CHANGED
@@ -1,8 +1,13 @@
1
  {
2
- "epoch": 10.0,
3
- "total_flos": 8948156034908160.0,
4
- "train_loss": 0.19590264558792114,
5
- "train_runtime": 49.0516,
6
- "train_samples_per_second": 7.339,
7
- "train_steps_per_second": 0.204
 
 
 
 
 
8
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.3651624619960785,
5
+ "eval_runtime": 0.2894,
6
+ "eval_samples_per_second": 13.821,
7
+ "eval_steps_per_second": 3.455,
8
+ "total_flos": 1.789631206981632e+16,
9
+ "train_loss": 0.08080000579357147,
10
+ "train_runtime": 92.7359,
11
+ "train_samples_per_second": 7.764,
12
+ "train_steps_per_second": 0.216
13
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.3651624619960785,
5
+ "eval_runtime": 0.2894,
6
+ "eval_samples_per_second": 13.821,
7
+ "eval_steps_per_second": 3.455
8
+ }
runs/Aug20_17-49-57_dcaf84c0e0bc/events.out.tfevents.1692553937.dcaf84c0e0bc.1053.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b49a3a63d276854a29cacfadb5f5c5a35b32bbd47dd36acae27702e65a664fa3
3
+ size 405
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 10.0,
3
- "total_flos": 8948156034908160.0,
4
- "train_loss": 0.19590264558792114,
5
- "train_runtime": 49.0516,
6
- "train_samples_per_second": 7.339,
7
- "train_steps_per_second": 0.204
8
  }
 
1
  {
2
+ "epoch": 20.0,
3
+ "total_flos": 1.789631206981632e+16,
4
+ "train_loss": 0.08080000579357147,
5
+ "train_runtime": 92.7359,
6
+ "train_samples_per_second": 7.764,
7
+ "train_steps_per_second": 0.216
8
  }
trainer_state.json CHANGED
@@ -1,121 +1,217 @@
1
  {
2
- "best_metric": 0.75,
3
- "best_model_checkpoint": "swin-tiny-patch4-window7-224-mulder-v-scully-colab/checkpoint-5",
4
- "epoch": 10.0,
5
- "global_step": 10,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "eval_accuracy": 0.25,
13
- "eval_loss": 0.8688191771507263,
14
- "eval_runtime": 0.2785,
15
- "eval_samples_per_second": 14.362,
16
- "eval_steps_per_second": 3.591,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 2.0,
21
- "eval_accuracy": 0.25,
22
- "eval_loss": 0.7692552804946899,
23
- "eval_runtime": 0.2993,
24
- "eval_samples_per_second": 13.366,
25
- "eval_steps_per_second": 3.341,
26
  "step": 2
27
  },
28
  {
29
  "epoch": 3.0,
30
- "eval_accuracy": 0.5,
31
- "eval_loss": 0.7055538892745972,
32
- "eval_runtime": 0.2815,
33
- "eval_samples_per_second": 14.211,
34
- "eval_steps_per_second": 3.553,
35
  "step": 3
36
  },
37
  {
38
  "epoch": 4.0,
39
  "eval_accuracy": 0.5,
40
- "eval_loss": 0.6579211950302124,
41
- "eval_runtime": 0.2933,
42
- "eval_samples_per_second": 13.636,
43
- "eval_steps_per_second": 3.409,
44
  "step": 4
45
  },
46
  {
47
  "epoch": 5.0,
48
- "eval_accuracy": 0.75,
49
- "eval_loss": 0.6105230450630188,
50
- "eval_runtime": 0.283,
51
- "eval_samples_per_second": 14.136,
52
- "eval_steps_per_second": 3.534,
53
  "step": 5
54
  },
55
  {
56
  "epoch": 6.0,
57
  "eval_accuracy": 0.75,
58
- "eval_loss": 0.601015031337738,
59
- "eval_runtime": 0.2817,
60
- "eval_samples_per_second": 14.202,
61
- "eval_steps_per_second": 3.55,
62
  "step": 6
63
  },
64
  {
65
  "epoch": 7.0,
66
  "eval_accuracy": 0.75,
67
- "eval_loss": 0.5963175892829895,
68
- "eval_runtime": 0.2889,
69
- "eval_samples_per_second": 13.845,
70
- "eval_steps_per_second": 3.461,
71
  "step": 7
72
  },
73
  {
74
  "epoch": 8.0,
75
- "eval_accuracy": 0.75,
76
- "eval_loss": 0.5912925601005554,
77
- "eval_runtime": 0.2873,
78
- "eval_samples_per_second": 13.924,
79
- "eval_steps_per_second": 3.481,
80
  "step": 8
81
  },
82
  {
83
  "epoch": 9.0,
84
- "eval_accuracy": 0.75,
85
- "eval_loss": 0.5851244926452637,
86
- "eval_runtime": 0.2874,
87
- "eval_samples_per_second": 13.917,
88
- "eval_steps_per_second": 3.479,
89
  "step": 9
90
  },
91
  {
92
  "epoch": 10.0,
93
- "learning_rate": 0.0,
94
- "loss": 0.1959,
95
  "step": 10
96
  },
97
  {
98
  "epoch": 10.0,
99
- "eval_accuracy": 0.75,
100
- "eval_loss": 0.5820506811141968,
101
- "eval_runtime": 0.2797,
102
- "eval_samples_per_second": 14.3,
103
- "eval_steps_per_second": 3.575,
104
  "step": 10
105
  },
106
  {
107
- "epoch": 10.0,
108
- "step": 10,
109
- "total_flos": 8948156034908160.0,
110
- "train_loss": 0.19590264558792114,
111
- "train_runtime": 49.0516,
112
- "train_samples_per_second": 7.339,
113
- "train_steps_per_second": 0.204
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
- "max_steps": 10,
117
- "num_train_epochs": 10,
118
- "total_flos": 8948156034908160.0,
119
  "trial_name": null,
120
  "trial_params": null
121
  }
 
1
  {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-mulder-v-scully-colab/checkpoint-8",
4
+ "epoch": 20.0,
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": 1.0,
12
+ "eval_accuracy": 0.75,
13
+ "eval_loss": 0.6105230450630188,
14
+ "eval_runtime": 0.2822,
15
+ "eval_samples_per_second": 14.173,
16
+ "eval_steps_per_second": 3.543,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 2.0,
21
+ "eval_accuracy": 0.5,
22
+ "eval_loss": 0.6975106596946716,
23
+ "eval_runtime": 0.2795,
24
+ "eval_samples_per_second": 14.311,
25
+ "eval_steps_per_second": 3.578,
26
  "step": 2
27
  },
28
  {
29
  "epoch": 3.0,
30
+ "eval_accuracy": 0.25,
31
+ "eval_loss": 0.8308714628219604,
32
+ "eval_runtime": 0.282,
33
+ "eval_samples_per_second": 14.186,
34
+ "eval_steps_per_second": 3.547,
35
  "step": 3
36
  },
37
  {
38
  "epoch": 4.0,
39
  "eval_accuracy": 0.5,
40
+ "eval_loss": 0.7603804469108582,
41
+ "eval_runtime": 0.2794,
42
+ "eval_samples_per_second": 14.316,
43
+ "eval_steps_per_second": 3.579,
44
  "step": 4
45
  },
46
  {
47
  "epoch": 5.0,
48
+ "eval_accuracy": 0.5,
49
+ "eval_loss": 0.6327458620071411,
50
+ "eval_runtime": 0.2816,
51
+ "eval_samples_per_second": 14.203,
52
+ "eval_steps_per_second": 3.551,
53
  "step": 5
54
  },
55
  {
56
  "epoch": 6.0,
57
  "eval_accuracy": 0.75,
58
+ "eval_loss": 0.5101333260536194,
59
+ "eval_runtime": 0.3029,
60
+ "eval_samples_per_second": 13.204,
61
+ "eval_steps_per_second": 3.301,
62
  "step": 6
63
  },
64
  {
65
  "epoch": 7.0,
66
  "eval_accuracy": 0.75,
67
+ "eval_loss": 0.41480666399002075,
68
+ "eval_runtime": 0.2864,
69
+ "eval_samples_per_second": 13.964,
70
+ "eval_steps_per_second": 3.491,
71
  "step": 7
72
  },
73
  {
74
  "epoch": 8.0,
75
+ "eval_accuracy": 1.0,
76
+ "eval_loss": 0.3651624619960785,
77
+ "eval_runtime": 0.2793,
78
+ "eval_samples_per_second": 14.319,
79
+ "eval_steps_per_second": 3.58,
80
  "step": 8
81
  },
82
  {
83
  "epoch": 9.0,
84
+ "eval_accuracy": 1.0,
85
+ "eval_loss": 0.34327611327171326,
86
+ "eval_runtime": 0.3008,
87
+ "eval_samples_per_second": 13.299,
88
+ "eval_steps_per_second": 3.325,
89
  "step": 9
90
  },
91
  {
92
  "epoch": 10.0,
93
+ "learning_rate": 2.777777777777778e-05,
94
+ "loss": 0.0984,
95
  "step": 10
96
  },
97
  {
98
  "epoch": 10.0,
99
+ "eval_accuracy": 1.0,
100
+ "eval_loss": 0.3231046795845032,
101
+ "eval_runtime": 0.296,
102
+ "eval_samples_per_second": 13.514,
103
+ "eval_steps_per_second": 3.379,
104
  "step": 10
105
  },
106
  {
107
+ "epoch": 11.0,
108
+ "eval_accuracy": 1.0,
109
+ "eval_loss": 0.30705589056015015,
110
+ "eval_runtime": 0.2953,
111
+ "eval_samples_per_second": 13.546,
112
+ "eval_steps_per_second": 3.386,
113
+ "step": 11
114
+ },
115
+ {
116
+ "epoch": 12.0,
117
+ "eval_accuracy": 1.0,
118
+ "eval_loss": 0.3047180771827698,
119
+ "eval_runtime": 0.3308,
120
+ "eval_samples_per_second": 12.092,
121
+ "eval_steps_per_second": 3.023,
122
+ "step": 12
123
+ },
124
+ {
125
+ "epoch": 13.0,
126
+ "eval_accuracy": 0.75,
127
+ "eval_loss": 0.3189181089401245,
128
+ "eval_runtime": 0.284,
129
+ "eval_samples_per_second": 14.083,
130
+ "eval_steps_per_second": 3.521,
131
+ "step": 13
132
+ },
133
+ {
134
+ "epoch": 14.0,
135
+ "eval_accuracy": 0.75,
136
+ "eval_loss": 0.343748539686203,
137
+ "eval_runtime": 0.3116,
138
+ "eval_samples_per_second": 12.839,
139
+ "eval_steps_per_second": 3.21,
140
+ "step": 14
141
+ },
142
+ {
143
+ "epoch": 15.0,
144
+ "eval_accuracy": 0.75,
145
+ "eval_loss": 0.3701111972332001,
146
+ "eval_runtime": 0.2886,
147
+ "eval_samples_per_second": 13.862,
148
+ "eval_steps_per_second": 3.466,
149
+ "step": 15
150
+ },
151
+ {
152
+ "epoch": 16.0,
153
+ "eval_accuracy": 0.75,
154
+ "eval_loss": 0.3959260582923889,
155
+ "eval_runtime": 0.2721,
156
+ "eval_samples_per_second": 14.698,
157
+ "eval_steps_per_second": 3.674,
158
+ "step": 16
159
+ },
160
+ {
161
+ "epoch": 17.0,
162
+ "eval_accuracy": 0.75,
163
+ "eval_loss": 0.41665372252464294,
164
+ "eval_runtime": 0.285,
165
+ "eval_samples_per_second": 14.034,
166
+ "eval_steps_per_second": 3.508,
167
+ "step": 17
168
+ },
169
+ {
170
+ "epoch": 18.0,
171
+ "eval_accuracy": 0.75,
172
+ "eval_loss": 0.41897234320640564,
173
+ "eval_runtime": 0.2854,
174
+ "eval_samples_per_second": 14.016,
175
+ "eval_steps_per_second": 3.504,
176
+ "step": 18
177
+ },
178
+ {
179
+ "epoch": 19.0,
180
+ "eval_accuracy": 0.75,
181
+ "eval_loss": 0.41535183787345886,
182
+ "eval_runtime": 0.2904,
183
+ "eval_samples_per_second": 13.773,
184
+ "eval_steps_per_second": 3.443,
185
+ "step": 19
186
+ },
187
+ {
188
+ "epoch": 20.0,
189
+ "learning_rate": 0.0,
190
+ "loss": 0.0632,
191
+ "step": 20
192
+ },
193
+ {
194
+ "epoch": 20.0,
195
+ "eval_accuracy": 0.75,
196
+ "eval_loss": 0.4113732874393463,
197
+ "eval_runtime": 0.2848,
198
+ "eval_samples_per_second": 14.047,
199
+ "eval_steps_per_second": 3.512,
200
+ "step": 20
201
+ },
202
+ {
203
+ "epoch": 20.0,
204
+ "step": 20,
205
+ "total_flos": 1.789631206981632e+16,
206
+ "train_loss": 0.08080000579357147,
207
+ "train_runtime": 92.7359,
208
+ "train_samples_per_second": 7.764,
209
+ "train_steps_per_second": 0.216
210
  }
211
  ],
212
+ "max_steps": 20,
213
+ "num_train_epochs": 20,
214
+ "total_flos": 1.789631206981632e+16,
215
  "trial_name": null,
216
  "trial_params": null
217
  }