Hugging Face's logo

zabir735
/
swin-tiny-patch4-window7-224-finetuned-batch8-nocrop2

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
zabir735 commited on
Commit
f8bb435
•
1 Parent(s): e925a31

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 +243 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.974619289340102,
3
+ "total_flos": 1.9487095364911104e+17,
4
+ "train_loss": 0.026832528186638897,
5
+ "train_runtime": 142.496,
6
+ "train_samples_per_second": 55.3,
7
+ "train_steps_per_second": 1.719
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.974619289340102,
3
+ "total_flos": 1.9487095364911104e+17,
4
+ "train_loss": 0.026832528186638897,
5
+ "train_runtime": 142.496,
6
+ "train_samples_per_second": 55.3,
7
+ "train_steps_per_second": 1.719
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9772727272727273,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-batch8-nocrop2/checkpoint-147",
4
+ "epoch": 4.974619289340102,
5
+ "eval_steps": 500,
6
+ "global_step": 245,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.20304568527918782,
13
+ "grad_norm": 0.18894483149051666,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.0212,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.40609137055837563,
20
+ "grad_norm": 24.582429885864258,
21
+ "learning_rate": 4e-05,
22
+ "loss": 0.0305,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.6091370558375635,
27
+ "grad_norm": 0.053805481642484665,
28
+ "learning_rate": 4.886363636363637e-05,
29
+ "loss": 0.0858,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.8121827411167513,
34
+ "grad_norm": 0.27398234605789185,
35
+ "learning_rate": 4.659090909090909e-05,
36
+ "loss": 0.0433,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.9949238578680203,
41
+ "eval_accuracy": 0.9545454545454546,
42
+ "eval_loss": 0.2792539596557617,
43
+ "eval_runtime": 1.4174,
44
+ "eval_samples_per_second": 124.175,
45
+ "eval_steps_per_second": 15.522,
46
+ "step": 49
47
+ },
48
+ {
49
+ "epoch": 1.015228426395939,
50
+ "grad_norm": 45.7299690246582,
51
+ "learning_rate": 4.431818181818182e-05,
52
+ "loss": 0.1388,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.218274111675127,
57
+ "grad_norm": 6.678280830383301,
58
+ "learning_rate": 4.204545454545455e-05,
59
+ "loss": 0.0434,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.4213197969543148,
64
+ "grad_norm": 22.982635498046875,
65
+ "learning_rate": 3.9772727272727275e-05,
66
+ "loss": 0.0735,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.6243654822335025,
71
+ "grad_norm": 21.329736709594727,
72
+ "learning_rate": 3.7500000000000003e-05,
73
+ "loss": 0.0162,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.8274111675126905,
78
+ "grad_norm": 27.677804946899414,
79
+ "learning_rate": 3.522727272727273e-05,
80
+ "loss": 0.0419,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 1.9898477157360406,
85
+ "eval_accuracy": 0.9715909090909091,
86
+ "eval_loss": 0.1445770561695099,
87
+ "eval_runtime": 1.4427,
88
+ "eval_samples_per_second": 121.992,
89
+ "eval_steps_per_second": 15.249,
90
+ "step": 98
91
+ },
92
+ {
93
+ "epoch": 2.030456852791878,
94
+ "grad_norm": 0.007859536446630955,
95
+ "learning_rate": 3.295454545454545e-05,
96
+ "loss": 0.0197,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.233502538071066,
101
+ "grad_norm": 0.011098887771368027,
102
+ "learning_rate": 3.068181818181818e-05,
103
+ "loss": 0.0097,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.436548223350254,
108
+ "grad_norm": 0.08474420756101608,
109
+ "learning_rate": 2.8409090909090912e-05,
110
+ "loss": 0.0037,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 2.6395939086294415,
115
+ "grad_norm": 0.013242855668067932,
116
+ "learning_rate": 2.6136363636363637e-05,
117
+ "loss": 0.0192,
118
+ "step": 130
119
+ },
120
+ {
121
+ "epoch": 2.8426395939086295,
122
+ "grad_norm": 0.17217466235160828,
123
+ "learning_rate": 2.3863636363636365e-05,
124
+ "loss": 0.0155,
125
+ "step": 140
126
+ },
127
+ {
128
+ "epoch": 2.984771573604061,
129
+ "eval_accuracy": 0.9772727272727273,
130
+ "eval_loss": 0.14674212038516998,
131
+ "eval_runtime": 1.4158,
132
+ "eval_samples_per_second": 124.312,
133
+ "eval_steps_per_second": 15.539,
134
+ "step": 147
135
+ },
136
+ {
137
+ "epoch": 3.045685279187817,
138
+ "grad_norm": 0.01039437111467123,
139
+ "learning_rate": 2.1590909090909093e-05,
140
+ "loss": 0.0271,
141
+ "step": 150
142
+ },
143
+ {
144
+ "epoch": 3.248730964467005,
145
+ "grad_norm": 0.007275668904185295,
146
+ "learning_rate": 1.9318181818181818e-05,
147
+ "loss": 0.0058,
148
+ "step": 160
149
+ },
150
+ {
151
+ "epoch": 3.451776649746193,
152
+ "grad_norm": 0.002001961227506399,
153
+ "learning_rate": 1.7045454545454546e-05,
154
+ "loss": 0.006,
155
+ "step": 170
156
+ },
157
+ {
158
+ "epoch": 3.6548223350253806,
159
+ "grad_norm": 0.0007674383814446628,
160
+ "learning_rate": 1.4772727272727274e-05,
161
+ "loss": 0.0005,
162
+ "step": 180
163
+ },
164
+ {
165
+ "epoch": 3.8578680203045685,
166
+ "grad_norm": 0.08923467248678207,
167
+ "learning_rate": 1.25e-05,
168
+ "loss": 0.0011,
169
+ "step": 190
170
+ },
171
+ {
172
+ "epoch": 4.0,
173
+ "eval_accuracy": 0.9602272727272727,
174
+ "eval_loss": 0.17827549576759338,
175
+ "eval_runtime": 1.4363,
176
+ "eval_samples_per_second": 122.539,
177
+ "eval_steps_per_second": 15.317,
178
+ "step": 197
179
+ },
180
+ {
181
+ "epoch": 4.060913705583756,
182
+ "grad_norm": 0.014368077740073204,
183
+ "learning_rate": 1.0227272727272729e-05,
184
+ "loss": 0.0376,
185
+ "step": 200
186
+ },
187
+ {
188
+ "epoch": 4.2639593908629445,
189
+ "grad_norm": 0.07785768061876297,
190
+ "learning_rate": 7.954545454545455e-06,
191
+ "loss": 0.0148,
192
+ "step": 210
193
+ },
194
+ {
195
+ "epoch": 4.467005076142132,
196
+ "grad_norm": 4.838421821594238,
197
+ "learning_rate": 5.681818181818182e-06,
198
+ "loss": 0.001,
199
+ "step": 220
200
+ },
201
+ {
202
+ "epoch": 4.67005076142132,
203
+ "grad_norm": 0.0007783414330333471,
204
+ "learning_rate": 3.409090909090909e-06,
205
+ "loss": 0.0001,
206
+ "step": 230
207
+ },
208
+ {
209
+ "epoch": 4.873096446700508,
210
+ "grad_norm": 6.467840194702148,
211
+ "learning_rate": 1.1363636363636364e-06,
212
+ "loss": 0.001,
213
+ "step": 240
214
+ },
215
+ {
216
+ "epoch": 4.974619289340102,
217
+ "eval_accuracy": 0.9659090909090909,
218
+ "eval_loss": 0.17341464757919312,
219
+ "eval_runtime": 1.4121,
220
+ "eval_samples_per_second": 124.639,
221
+ "eval_steps_per_second": 15.58,
222
+ "step": 245
223
+ },
224
+ {
225
+ "epoch": 4.974619289340102,
226
+ "step": 245,
227
+ "total_flos": 1.9487095364911104e+17,
228
+ "train_loss": 0.026832528186638897,
229
+ "train_runtime": 142.496,
230
+ "train_samples_per_second": 55.3,
231
+ "train_steps_per_second": 1.719
232
+ }
233
+ ],
234
+ "logging_steps": 10,
235
+ "max_steps": 245,
236
+ "num_input_tokens_seen": 0,
237
+ "num_train_epochs": 5,
238
+ "save_steps": 500,
239
+ "total_flos": 1.9487095364911104e+17,
240
+ "train_batch_size": 8,
241
+ "trial_name": null,
242
+ "trial_params": null
243
+ }