hoanbklucky commited on
Commit
004ebef
·
verified ·
1 Parent(s): 61bf77e

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -2
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. train_results.json +8 -0
  5. trainer_state.json +286 -0
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/efficientnet-b0](https://huggingface.co/google/efficientnet-b0) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4139
22
- - Accuracy: 0.8621
23
 
24
  ## Model description
25
 
 
18
 
19
  This model is a fine-tuned version of [google/efficientnet-b0](https://huggingface.co/google/efficientnet-b0) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3784
22
+ - Accuracy: 0.8883
23
 
24
  ## Model description
25
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.577777777777778,
3
+ "eval_accuracy": 0.8883415435139573,
4
+ "eval_loss": 0.3784164488315582,
5
+ "eval_runtime": 61.5643,
6
+ "eval_samples_per_second": 9.892,
7
+ "eval_steps_per_second": 0.633,
8
+ "total_flos": 4.991931114153984e+16,
9
+ "train_loss": 0.42888181643052536,
10
+ "train_runtime": 2265.5727,
11
+ "train_samples_per_second": 6.352,
12
+ "train_steps_per_second": 0.097
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.577777777777778,
3
+ "eval_accuracy": 0.8883415435139573,
4
+ "eval_loss": 0.3784164488315582,
5
+ "eval_runtime": 61.5643,
6
+ "eval_samples_per_second": 9.892,
7
+ "eval_steps_per_second": 0.633
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.577777777777778,
3
+ "total_flos": 4.991931114153984e+16,
4
+ "train_loss": 0.42888181643052536,
5
+ "train_runtime": 2265.5727,
6
+ "train_samples_per_second": 6.352,
7
+ "train_steps_per_second": 0.097
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,286 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8883415435139573,
3
+ "best_model_checkpoint": "efficientnet-b0-finetuned-noh\\checkpoint-184",
4
+ "epoch": 9.577777777777778,
5
+ "eval_steps": 500,
6
+ "global_step": 220,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4444444444444444,
13
+ "grad_norm": 8.235955238342285,
14
+ "learning_rate": 2.272727272727273e-05,
15
+ "loss": 0.6411,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.8888888888888888,
20
+ "grad_norm": 7.751129150390625,
21
+ "learning_rate": 4.545454545454546e-05,
22
+ "loss": 0.6146,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_accuracy": 0.729064039408867,
28
+ "eval_loss": 0.6138808727264404,
29
+ "eval_runtime": 88.9218,
30
+ "eval_samples_per_second": 6.849,
31
+ "eval_steps_per_second": 0.439,
32
+ "step": 23
33
+ },
34
+ {
35
+ "epoch": 1.3111111111111111,
36
+ "grad_norm": 6.260272979736328,
37
+ "learning_rate": 4.797979797979798e-05,
38
+ "loss": 0.5289,
39
+ "step": 30
40
+ },
41
+ {
42
+ "epoch": 1.7555555555555555,
43
+ "grad_norm": 5.691160202026367,
44
+ "learning_rate": 4.545454545454546e-05,
45
+ "loss": 0.5116,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_accuracy": 0.8308702791461412,
51
+ "eval_loss": 0.47041037678718567,
52
+ "eval_runtime": 85.525,
53
+ "eval_samples_per_second": 7.121,
54
+ "eval_steps_per_second": 0.456,
55
+ "step": 46
56
+ },
57
+ {
58
+ "epoch": 2.1777777777777776,
59
+ "grad_norm": 5.566213130950928,
60
+ "learning_rate": 4.292929292929293e-05,
61
+ "loss": 0.4151,
62
+ "step": 50
63
+ },
64
+ {
65
+ "epoch": 2.6222222222222222,
66
+ "grad_norm": 5.660247325897217,
67
+ "learning_rate": 4.0404040404040405e-05,
68
+ "loss": 0.4655,
69
+ "step": 60
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_accuracy": 0.8587848932676518,
74
+ "eval_loss": 0.4233274757862091,
75
+ "eval_runtime": 62.7576,
76
+ "eval_samples_per_second": 9.704,
77
+ "eval_steps_per_second": 0.621,
78
+ "step": 69
79
+ },
80
+ {
81
+ "epoch": 3.0444444444444443,
82
+ "grad_norm": 5.13922119140625,
83
+ "learning_rate": 3.787878787878788e-05,
84
+ "loss": 0.4394,
85
+ "step": 70
86
+ },
87
+ {
88
+ "epoch": 3.488888888888889,
89
+ "grad_norm": 5.63355827331543,
90
+ "learning_rate": 3.535353535353535e-05,
91
+ "loss": 0.4292,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 3.9333333333333336,
96
+ "grad_norm": 6.373378276824951,
97
+ "learning_rate": 3.282828282828283e-05,
98
+ "loss": 0.4331,
99
+ "step": 90
100
+ },
101
+ {
102
+ "epoch": 4.0,
103
+ "eval_accuracy": 0.8604269293924466,
104
+ "eval_loss": 0.41187092661857605,
105
+ "eval_runtime": 62.2366,
106
+ "eval_samples_per_second": 9.785,
107
+ "eval_steps_per_second": 0.627,
108
+ "step": 92
109
+ },
110
+ {
111
+ "epoch": 4.355555555555555,
112
+ "grad_norm": 5.6973114013671875,
113
+ "learning_rate": 3.0303030303030306e-05,
114
+ "loss": 0.388,
115
+ "step": 100
116
+ },
117
+ {
118
+ "epoch": 4.8,
119
+ "grad_norm": 6.741119861602783,
120
+ "learning_rate": 2.777777777777778e-05,
121
+ "loss": 0.4281,
122
+ "step": 110
123
+ },
124
+ {
125
+ "epoch": 5.0,
126
+ "eval_accuracy": 0.8752052545155994,
127
+ "eval_loss": 0.38966891169548035,
128
+ "eval_runtime": 62.2405,
129
+ "eval_samples_per_second": 9.785,
130
+ "eval_steps_per_second": 0.627,
131
+ "step": 115
132
+ },
133
+ {
134
+ "epoch": 5.222222222222222,
135
+ "grad_norm": 5.320347785949707,
136
+ "learning_rate": 2.5252525252525256e-05,
137
+ "loss": 0.3975,
138
+ "step": 120
139
+ },
140
+ {
141
+ "epoch": 5.666666666666667,
142
+ "grad_norm": 5.142993927001953,
143
+ "learning_rate": 2.272727272727273e-05,
144
+ "loss": 0.4001,
145
+ "step": 130
146
+ },
147
+ {
148
+ "epoch": 6.0,
149
+ "eval_accuracy": 0.8719211822660099,
150
+ "eval_loss": 0.4011945426464081,
151
+ "eval_runtime": 63.0341,
152
+ "eval_samples_per_second": 9.661,
153
+ "eval_steps_per_second": 0.619,
154
+ "step": 138
155
+ },
156
+ {
157
+ "epoch": 6.088888888888889,
158
+ "grad_norm": 4.859269142150879,
159
+ "learning_rate": 2.0202020202020203e-05,
160
+ "loss": 0.34,
161
+ "step": 140
162
+ },
163
+ {
164
+ "epoch": 6.533333333333333,
165
+ "grad_norm": 6.196608066558838,
166
+ "learning_rate": 1.7676767676767676e-05,
167
+ "loss": 0.4207,
168
+ "step": 150
169
+ },
170
+ {
171
+ "epoch": 6.977777777777778,
172
+ "grad_norm": 6.519267559051514,
173
+ "learning_rate": 1.5151515151515153e-05,
174
+ "loss": 0.3721,
175
+ "step": 160
176
+ },
177
+ {
178
+ "epoch": 7.0,
179
+ "eval_accuracy": 0.8817733990147784,
180
+ "eval_loss": 0.38614729046821594,
181
+ "eval_runtime": 62.6292,
182
+ "eval_samples_per_second": 9.724,
183
+ "eval_steps_per_second": 0.623,
184
+ "step": 161
185
+ },
186
+ {
187
+ "epoch": 7.4,
188
+ "grad_norm": 4.774895668029785,
189
+ "learning_rate": 1.2626262626262628e-05,
190
+ "loss": 0.3456,
191
+ "step": 170
192
+ },
193
+ {
194
+ "epoch": 7.844444444444444,
195
+ "grad_norm": 6.236260890960693,
196
+ "learning_rate": 1.0101010101010101e-05,
197
+ "loss": 0.3979,
198
+ "step": 180
199
+ },
200
+ {
201
+ "epoch": 8.0,
202
+ "eval_accuracy": 0.8883415435139573,
203
+ "eval_loss": 0.3784164488315582,
204
+ "eval_runtime": 62.8885,
205
+ "eval_samples_per_second": 9.684,
206
+ "eval_steps_per_second": 0.62,
207
+ "step": 184
208
+ },
209
+ {
210
+ "epoch": 8.266666666666667,
211
+ "grad_norm": 7.606906890869141,
212
+ "learning_rate": 7.5757575757575764e-06,
213
+ "loss": 0.3784,
214
+ "step": 190
215
+ },
216
+ {
217
+ "epoch": 8.71111111111111,
218
+ "grad_norm": 4.811132907867432,
219
+ "learning_rate": 5.050505050505051e-06,
220
+ "loss": 0.3376,
221
+ "step": 200
222
+ },
223
+ {
224
+ "epoch": 9.0,
225
+ "eval_accuracy": 0.8604269293924466,
226
+ "eval_loss": 0.4170529246330261,
227
+ "eval_runtime": 62.9062,
228
+ "eval_samples_per_second": 9.681,
229
+ "eval_steps_per_second": 0.62,
230
+ "step": 207
231
+ },
232
+ {
233
+ "epoch": 9.133333333333333,
234
+ "grad_norm": 5.669275760650635,
235
+ "learning_rate": 2.5252525252525253e-06,
236
+ "loss": 0.3526,
237
+ "step": 210
238
+ },
239
+ {
240
+ "epoch": 9.577777777777778,
241
+ "grad_norm": 6.406429767608643,
242
+ "learning_rate": 0.0,
243
+ "loss": 0.3984,
244
+ "step": 220
245
+ },
246
+ {
247
+ "epoch": 9.577777777777778,
248
+ "eval_accuracy": 0.8620689655172413,
249
+ "eval_loss": 0.4138999581336975,
250
+ "eval_runtime": 63.2813,
251
+ "eval_samples_per_second": 9.624,
252
+ "eval_steps_per_second": 0.616,
253
+ "step": 220
254
+ },
255
+ {
256
+ "epoch": 9.577777777777778,
257
+ "step": 220,
258
+ "total_flos": 4.991931114153984e+16,
259
+ "train_loss": 0.42888181643052536,
260
+ "train_runtime": 2265.5727,
261
+ "train_samples_per_second": 6.352,
262
+ "train_steps_per_second": 0.097
263
+ }
264
+ ],
265
+ "logging_steps": 10,
266
+ "max_steps": 220,
267
+ "num_input_tokens_seen": 0,
268
+ "num_train_epochs": 10,
269
+ "save_steps": 500,
270
+ "stateful_callbacks": {
271
+ "TrainerControl": {
272
+ "args": {
273
+ "should_epoch_stop": false,
274
+ "should_evaluate": false,
275
+ "should_log": false,
276
+ "should_save": true,
277
+ "should_training_stop": true
278
+ },
279
+ "attributes": {}
280
+ }
281
+ },
282
+ "total_flos": 4.991931114153984e+16,
283
+ "train_batch_size": 16,
284
+ "trial_name": null,
285
+ "trial_params": null
286
+ }