Hugging Face's logo

howdyaendra
/
microsoft-swinv2-small-patch4-window16-256-finetuned-xblockm

Image Classification
Transformers
ONNX
Safetensors
swinv2
Generated from Trainer
Model card Files Community
howdyaendra commited on
Commit
64025ce
·
verified ·
1 Parent(s): a8f0a5d

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +226 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.901234567901234,
3
+ "total_flos": 4.522715256123187e+17,
4
+ "train_loss": 0.19196589663624763,
5
+ "train_runtime": 9159.5769,
6
+ "train_samples_per_second": 1.13,
7
+ "train_steps_per_second": 0.017
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.901234567901234,
3
+ "total_flos": 4.522715256123187e+17,
4
+ "train_loss": 0.19196589663624763,
5
+ "train_runtime": 9159.5769,
6
+ "train_samples_per_second": 1.13,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9535481125844637,
3
+ "best_model_checkpoint": "microsoft-swinv2-small-patch4-window16-256-finetuned-xblockm\\checkpoint-160",
4
+ "epoch": 7.901234567901234,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.49382716049382713,
13
+ "grad_norm": 1.6179720163345337,
14
+ "learning_rate": 1.5503875968992248e-05,
15
+ "loss": 0.6579,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.9876543209876543,
20
+ "grad_norm": 2.4816274642944336,
21
+ "learning_rate": 3.1007751937984497e-05,
22
+ "loss": 0.4357,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.9876543209876543,
27
+ "eval_loss": 0.2544282078742981,
28
+ "eval_roc_auc": 0.7784430091957527,
29
+ "eval_runtime": 57.6433,
30
+ "eval_samples_per_second": 5.621,
31
+ "eval_steps_per_second": 0.364,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 1.4814814814814814,
36
+ "grad_norm": 1.2008687257766724,
37
+ "learning_rate": 4.651162790697675e-05,
38
+ "loss": 0.2163,
39
+ "step": 30
40
+ },
41
+ {
42
+ "epoch": 1.9753086419753085,
43
+ "grad_norm": 1.6955859661102295,
44
+ "learning_rate": 6.201550387596899e-05,
45
+ "loss": 0.2027,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 1.9753086419753085,
50
+ "eval_loss": 0.20164352655410767,
51
+ "eval_roc_auc": 0.8430768302596149,
52
+ "eval_runtime": 62.1569,
53
+ "eval_samples_per_second": 5.213,
54
+ "eval_steps_per_second": 0.338,
55
+ "step": 40
56
+ },
57
+ {
58
+ "epoch": 2.4691358024691357,
59
+ "grad_norm": 0.869544267654419,
60
+ "learning_rate": 7.751937984496124e-05,
61
+ "loss": 0.1889,
62
+ "step": 50
63
+ },
64
+ {
65
+ "epoch": 2.962962962962963,
66
+ "grad_norm": 0.8159006834030151,
67
+ "learning_rate": 9.30232558139535e-05,
68
+ "loss": 0.1743,
69
+ "step": 60
70
+ },
71
+ {
72
+ "epoch": 2.962962962962963,
73
+ "eval_loss": 0.17011196911334991,
74
+ "eval_roc_auc": 0.8911886208911244,
75
+ "eval_runtime": 79.4085,
76
+ "eval_samples_per_second": 4.08,
77
+ "eval_steps_per_second": 0.264,
78
+ "step": 60
79
+ },
80
+ {
81
+ "epoch": 3.45679012345679,
82
+ "grad_norm": 0.8456718921661377,
83
+ "learning_rate": 0.00010852713178294573,
84
+ "loss": 0.1567,
85
+ "step": 70
86
+ },
87
+ {
88
+ "epoch": 3.950617283950617,
89
+ "grad_norm": 0.9450457692146301,
90
+ "learning_rate": 0.00012403100775193799,
91
+ "loss": 0.1625,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 4.0,
96
+ "eval_loss": 0.16766950488090515,
97
+ "eval_roc_auc": 0.9083226959813038,
98
+ "eval_runtime": 84.3656,
99
+ "eval_samples_per_second": 3.84,
100
+ "eval_steps_per_second": 0.249,
101
+ "step": 81
102
+ },
103
+ {
104
+ "epoch": 4.444444444444445,
105
+ "grad_norm": 0.6654064655303955,
106
+ "learning_rate": 0.00013953488372093025,
107
+ "loss": 0.1553,
108
+ "step": 90
109
+ },
110
+ {
111
+ "epoch": 4.938271604938271,
112
+ "grad_norm": 0.7665498852729797,
113
+ "learning_rate": 0.0001550387596899225,
114
+ "loss": 0.1321,
115
+ "step": 100
116
+ },
117
+ {
118
+ "epoch": 4.987654320987654,
119
+ "eval_loss": 0.144697904586792,
120
+ "eval_roc_auc": 0.9246192780572068,
121
+ "eval_runtime": 39.0205,
122
+ "eval_samples_per_second": 8.303,
123
+ "eval_steps_per_second": 0.538,
124
+ "step": 101
125
+ },
126
+ {
127
+ "epoch": 5.432098765432099,
128
+ "grad_norm": 0.6621432900428772,
129
+ "learning_rate": 0.00017054263565891473,
130
+ "loss": 0.1232,
131
+ "step": 110
132
+ },
133
+ {
134
+ "epoch": 5.925925925925926,
135
+ "grad_norm": 0.7424349188804626,
136
+ "learning_rate": 0.000186046511627907,
137
+ "loss": 0.1155,
138
+ "step": 120
139
+ },
140
+ {
141
+ "epoch": 5.9753086419753085,
142
+ "eval_loss": 0.14180859923362732,
143
+ "eval_roc_auc": 0.9311112381242697,
144
+ "eval_runtime": 132.4426,
145
+ "eval_samples_per_second": 2.446,
146
+ "eval_steps_per_second": 0.159,
147
+ "step": 121
148
+ },
149
+ {
150
+ "epoch": 6.419753086419753,
151
+ "grad_norm": 0.6604060530662537,
152
+ "learning_rate": 0.00019999963640522314,
153
+ "loss": 0.1009,
154
+ "step": 130
155
+ },
156
+ {
157
+ "epoch": 6.91358024691358,
158
+ "grad_norm": 0.7176498174667358,
159
+ "learning_rate": 0.0001999560082311786,
160
+ "loss": 0.0959,
161
+ "step": 140
162
+ },
163
+ {
164
+ "epoch": 6.962962962962963,
165
+ "eval_loss": 0.13807977735996246,
166
+ "eval_roc_auc": 0.9460352842554489,
167
+ "eval_runtime": 148.6943,
168
+ "eval_samples_per_second": 2.179,
169
+ "eval_steps_per_second": 0.141,
170
+ "step": 141
171
+ },
172
+ {
173
+ "epoch": 7.407407407407407,
174
+ "grad_norm": 0.7749078869819641,
175
+ "learning_rate": 0.0001998396974527365,
176
+ "loss": 0.0748,
177
+ "step": 150
178
+ },
179
+ {
180
+ "epoch": 7.901234567901234,
181
+ "grad_norm": 0.5961336493492126,
182
+ "learning_rate": 0.00019965078864480587,
183
+ "loss": 0.0788,
184
+ "step": 160
185
+ },
186
+ {
187
+ "epoch": 7.901234567901234,
188
+ "eval_loss": 0.12518148124217987,
189
+ "eval_roc_auc": 0.9535481125844637,
190
+ "eval_runtime": 101.3985,
191
+ "eval_samples_per_second": 3.195,
192
+ "eval_steps_per_second": 0.207,
193
+ "step": 160
194
+ },
195
+ {
196
+ "epoch": 7.901234567901234,
197
+ "step": 160,
198
+ "total_flos": 4.522715256123187e+17,
199
+ "train_loss": 0.19196589663624763,
200
+ "train_runtime": 9159.5769,
201
+ "train_samples_per_second": 1.13,
202
+ "train_steps_per_second": 0.017
203
+ }
204
+ ],
205
+ "logging_steps": 10,
206
+ "max_steps": 160,
207
+ "num_input_tokens_seen": 0,
208
+ "num_train_epochs": 8,
209
+ "save_steps": 500,
210
+ "stateful_callbacks": {
211
+ "TrainerControl": {
212
+ "args": {
213
+ "should_epoch_stop": false,
214
+ "should_evaluate": false,
215
+ "should_log": false,
216
+ "should_save": true,
217
+ "should_training_stop": true
218
+ },
219
+ "attributes": {}
220
+ }
221
+ },
222
+ "total_flos": 4.522715256123187e+17,
223
+ "train_batch_size": 16,
224
+ "trial_name": null,
225
+ "trial_params": null
226
+ }