mariamoracrossitcr commited on
Commit
56bb049
1 Parent(s): 94d828a

🍻 cheers

Browse files
README.md CHANGED
@@ -2,6 +2,7 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # vit-base-beans-demo-v7
17
 
18
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0571
21
- - Accuracy: 0.9850
22
 
23
  ## Model description
24
 
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
+ - image-classification
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
16
 
17
  # vit-base-beans-demo-v7
18
 
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0492
22
+ - Accuracy: 0.9925
23
 
24
  ## Model description
25
 
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 4.0,
3
  "eval_accuracy": 0.9924812030075187,
4
- "eval_loss": 0.042201049625873566,
5
- "eval_runtime": 1.5136,
6
- "eval_samples_per_second": 87.868,
7
- "eval_steps_per_second": 11.231,
8
  "total_flos": 3.205097416476426e+17,
9
- "train_loss": 0.11964335679434814,
10
- "train_runtime": 100.8137,
11
- "train_samples_per_second": 41.026,
12
- "train_steps_per_second": 2.579
13
  }
 
1
  {
2
  "epoch": 4.0,
3
  "eval_accuracy": 0.9924812030075187,
4
+ "eval_loss": 0.0491877980530262,
5
+ "eval_runtime": 1.5785,
6
+ "eval_samples_per_second": 84.255,
7
+ "eval_steps_per_second": 10.769,
8
  "total_flos": 3.205097416476426e+17,
9
+ "train_loss": 0.12038601376116276,
10
+ "train_runtime": 77.0575,
11
+ "train_samples_per_second": 53.674,
12
+ "train_steps_per_second": 3.374
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
  "eval_accuracy": 0.9924812030075187,
4
- "eval_loss": 0.042201049625873566,
5
- "eval_runtime": 1.5136,
6
- "eval_samples_per_second": 87.868,
7
- "eval_steps_per_second": 11.231
8
  }
 
1
  {
2
  "epoch": 4.0,
3
  "eval_accuracy": 0.9924812030075187,
4
+ "eval_loss": 0.0491877980530262,
5
+ "eval_runtime": 1.5785,
6
+ "eval_samples_per_second": 84.255,
7
+ "eval_steps_per_second": 10.769
8
  }
runs/Jun10_21-44-02_39bec5d8a054/events.out.tfevents.1718056013.39bec5d8a054.1252.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f625cf02346e976e244840791cda40eda3183918bb28e0db64dbd122de4164d
3
+ size 411
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
  "total_flos": 3.205097416476426e+17,
4
- "train_loss": 0.11964335679434814,
5
- "train_runtime": 100.8137,
6
- "train_samples_per_second": 41.026,
7
- "train_steps_per_second": 2.579
8
  }
 
1
  {
2
  "epoch": 4.0,
3
  "total_flos": 3.205097416476426e+17,
4
+ "train_loss": 0.12038601376116276,
5
+ "train_runtime": 77.0575,
6
+ "train_samples_per_second": 53.674,
7
+ "train_steps_per_second": 3.374
8
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.042201049625873566,
3
- "best_model_checkpoint": "./vit-base-beans-demo-v7/checkpoint-200",
4
  "epoch": 4.0,
5
  "eval_steps": 100,
6
  "global_step": 260,
@@ -10,212 +10,212 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.15384615384615385,
13
- "grad_norm": 1.7636618614196777,
14
  "learning_rate": 0.00019230769230769233,
15
- "loss": 0.8443,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.3076923076923077,
20
- "grad_norm": 1.1493185758590698,
21
  "learning_rate": 0.00018461538461538463,
22
- "loss": 0.3526,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.46153846153846156,
27
- "grad_norm": 0.6322227120399475,
28
  "learning_rate": 0.00017692307692307693,
29
- "loss": 0.2377,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.6153846153846154,
34
- "grad_norm": 0.7355738282203674,
35
  "learning_rate": 0.00016923076923076923,
36
- "loss": 0.2375,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.7692307692307693,
41
- "grad_norm": 0.3265851140022278,
42
  "learning_rate": 0.00016153846153846155,
43
- "loss": 0.2825,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.9230769230769231,
48
- "grad_norm": 0.9981272220611572,
49
  "learning_rate": 0.00015384615384615385,
50
- "loss": 0.2397,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 1.0769230769230769,
55
- "grad_norm": 3.7455718517303467,
56
  "learning_rate": 0.00014615384615384615,
57
- "loss": 0.1233,
58
  "step": 70
59
  },
60
  {
61
  "epoch": 1.2307692307692308,
62
- "grad_norm": 3.8250844478607178,
63
  "learning_rate": 0.00013846153846153847,
64
- "loss": 0.1297,
65
  "step": 80
66
  },
67
  {
68
  "epoch": 1.3846153846153846,
69
- "grad_norm": 0.28349635004997253,
70
  "learning_rate": 0.00013076923076923077,
71
- "loss": 0.0927,
72
  "step": 90
73
  },
74
  {
75
  "epoch": 1.5384615384615383,
76
- "grad_norm": 1.9211033582687378,
77
  "learning_rate": 0.0001230769230769231,
78
- "loss": 0.0686,
79
  "step": 100
80
  },
81
  {
82
  "epoch": 1.5384615384615383,
83
- "eval_accuracy": 0.9849624060150376,
84
- "eval_loss": 0.07935579121112823,
85
- "eval_runtime": 1.7219,
86
- "eval_samples_per_second": 77.239,
87
- "eval_steps_per_second": 9.873,
88
  "step": 100
89
  },
90
  {
91
  "epoch": 1.6923076923076923,
92
- "grad_norm": 2.195355176925659,
93
  "learning_rate": 0.00011538461538461538,
94
- "loss": 0.1031,
95
  "step": 110
96
  },
97
  {
98
  "epoch": 1.8461538461538463,
99
- "grad_norm": 0.32399165630340576,
100
  "learning_rate": 0.0001076923076923077,
101
- "loss": 0.1192,
102
  "step": 120
103
  },
104
  {
105
  "epoch": 2.0,
106
- "grad_norm": 0.09631959348917007,
107
  "learning_rate": 0.0001,
108
- "loss": 0.022,
109
  "step": 130
110
  },
111
  {
112
  "epoch": 2.1538461538461537,
113
- "grad_norm": 0.0886223167181015,
114
  "learning_rate": 9.230769230769232e-05,
115
- "loss": 0.0342,
116
  "step": 140
117
  },
118
  {
119
  "epoch": 2.3076923076923075,
120
- "grad_norm": 0.1216232031583786,
121
  "learning_rate": 8.461538461538461e-05,
122
- "loss": 0.0176,
123
  "step": 150
124
  },
125
  {
126
  "epoch": 2.4615384615384617,
127
- "grad_norm": 0.0750468522310257,
128
  "learning_rate": 7.692307692307693e-05,
129
- "loss": 0.0366,
130
  "step": 160
131
  },
132
  {
133
  "epoch": 2.6153846153846154,
134
- "grad_norm": 0.07128575444221497,
135
  "learning_rate": 6.923076923076924e-05,
136
- "loss": 0.0144,
137
  "step": 170
138
  },
139
  {
140
  "epoch": 2.769230769230769,
141
- "grad_norm": 3.5829079151153564,
142
  "learning_rate": 6.153846153846155e-05,
143
- "loss": 0.0536,
144
  "step": 180
145
  },
146
  {
147
  "epoch": 2.9230769230769234,
148
- "grad_norm": 1.5514700412750244,
149
  "learning_rate": 5.384615384615385e-05,
150
- "loss": 0.0146,
151
  "step": 190
152
  },
153
  {
154
  "epoch": 3.076923076923077,
155
- "grad_norm": 0.061695199459791183,
156
  "learning_rate": 4.615384615384616e-05,
157
- "loss": 0.0125,
158
  "step": 200
159
  },
160
  {
161
  "epoch": 3.076923076923077,
162
- "eval_accuracy": 0.9924812030075187,
163
- "eval_loss": 0.042201049625873566,
164
- "eval_runtime": 1.2489,
165
- "eval_samples_per_second": 106.492,
166
- "eval_steps_per_second": 13.612,
167
  "step": 200
168
  },
169
  {
170
  "epoch": 3.230769230769231,
171
- "grad_norm": 0.060515470802783966,
172
  "learning_rate": 3.846153846153846e-05,
173
- "loss": 0.0124,
174
  "step": 210
175
  },
176
  {
177
  "epoch": 3.3846153846153846,
178
- "grad_norm": 0.06038433685898781,
179
  "learning_rate": 3.0769230769230774e-05,
180
- "loss": 0.0114,
181
  "step": 220
182
  },
183
  {
184
  "epoch": 3.5384615384615383,
185
- "grad_norm": 0.0607147179543972,
186
  "learning_rate": 2.307692307692308e-05,
187
- "loss": 0.0169,
188
  "step": 230
189
  },
190
  {
191
  "epoch": 3.6923076923076925,
192
- "grad_norm": 0.058113083243370056,
193
  "learning_rate": 1.5384615384615387e-05,
194
- "loss": 0.011,
195
  "step": 240
196
  },
197
  {
198
  "epoch": 3.8461538461538463,
199
- "grad_norm": 0.06449621915817261,
200
  "learning_rate": 7.692307692307694e-06,
201
- "loss": 0.0111,
202
  "step": 250
203
  },
204
  {
205
  "epoch": 4.0,
206
- "grad_norm": 0.08513768017292023,
207
  "learning_rate": 0.0,
208
- "loss": 0.0112,
209
  "step": 260
210
  },
211
  {
212
  "epoch": 4.0,
213
  "step": 260,
214
  "total_flos": 3.205097416476426e+17,
215
- "train_loss": 0.11964335679434814,
216
- "train_runtime": 100.8137,
217
- "train_samples_per_second": 41.026,
218
- "train_steps_per_second": 2.579
219
  }
220
  ],
221
  "logging_steps": 10,
 
1
  {
2
+ "best_metric": 0.0491877980530262,
3
+ "best_model_checkpoint": "./vit-base-beans-demo-v7/checkpoint-100",
4
  "epoch": 4.0,
5
  "eval_steps": 100,
6
  "global_step": 260,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.15384615384615385,
13
+ "grad_norm": 1.6902730464935303,
14
  "learning_rate": 0.00019230769230769233,
15
+ "loss": 0.7748,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.3076923076923077,
20
+ "grad_norm": 1.2790460586547852,
21
  "learning_rate": 0.00018461538461538463,
22
+ "loss": 0.2739,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.46153846153846156,
27
+ "grad_norm": 0.7741395235061646,
28
  "learning_rate": 0.00017692307692307693,
29
+ "loss": 0.1927,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.6153846153846154,
34
+ "grad_norm": 5.114573001861572,
35
  "learning_rate": 0.00016923076923076923,
36
+ "loss": 0.2443,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.7692307692307693,
41
+ "grad_norm": 15.121728897094727,
42
  "learning_rate": 0.00016153846153846155,
43
+ "loss": 0.2038,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.9230769230769231,
48
+ "grad_norm": 3.094726324081421,
49
  "learning_rate": 0.00015384615384615385,
50
+ "loss": 0.2427,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 1.0769230769230769,
55
+ "grad_norm": 0.9401968717575073,
56
  "learning_rate": 0.00014615384615384615,
57
+ "loss": 0.179,
58
  "step": 70
59
  },
60
  {
61
  "epoch": 1.2307692307692308,
62
+ "grad_norm": 0.16439810395240784,
63
  "learning_rate": 0.00013846153846153847,
64
+ "loss": 0.1334,
65
  "step": 80
66
  },
67
  {
68
  "epoch": 1.3846153846153846,
69
+ "grad_norm": 0.1418611705303192,
70
  "learning_rate": 0.00013076923076923077,
71
+ "loss": 0.1166,
72
  "step": 90
73
  },
74
  {
75
  "epoch": 1.5384615384615383,
76
+ "grad_norm": 1.5957568883895874,
77
  "learning_rate": 0.0001230769230769231,
78
+ "loss": 0.0862,
79
  "step": 100
80
  },
81
  {
82
  "epoch": 1.5384615384615383,
83
+ "eval_accuracy": 0.9924812030075187,
84
+ "eval_loss": 0.0491877980530262,
85
+ "eval_runtime": 1.3534,
86
+ "eval_samples_per_second": 98.272,
87
+ "eval_steps_per_second": 12.561,
88
  "step": 100
89
  },
90
  {
91
  "epoch": 1.6923076923076923,
92
+ "grad_norm": 1.3301724195480347,
93
  "learning_rate": 0.00011538461538461538,
94
+ "loss": 0.1008,
95
  "step": 110
96
  },
97
  {
98
  "epoch": 1.8461538461538463,
99
+ "grad_norm": 0.32133230566978455,
100
  "learning_rate": 0.0001076923076923077,
101
+ "loss": 0.0803,
102
  "step": 120
103
  },
104
  {
105
  "epoch": 2.0,
106
+ "grad_norm": 0.4987194836139679,
107
  "learning_rate": 0.0001,
108
+ "loss": 0.0777,
109
  "step": 130
110
  },
111
  {
112
  "epoch": 2.1538461538461537,
113
+ "grad_norm": 3.434934377670288,
114
  "learning_rate": 9.230769230769232e-05,
115
+ "loss": 0.0583,
116
  "step": 140
117
  },
118
  {
119
  "epoch": 2.3076923076923075,
120
+ "grad_norm": 0.08973214775323868,
121
  "learning_rate": 8.461538461538461e-05,
122
+ "loss": 0.0796,
123
  "step": 150
124
  },
125
  {
126
  "epoch": 2.4615384615384617,
127
+ "grad_norm": 0.0839068666100502,
128
  "learning_rate": 7.692307692307693e-05,
129
+ "loss": 0.0468,
130
  "step": 160
131
  },
132
  {
133
  "epoch": 2.6153846153846154,
134
+ "grad_norm": 0.265321284532547,
135
  "learning_rate": 6.923076923076924e-05,
136
+ "loss": 0.0204,
137
  "step": 170
138
  },
139
  {
140
  "epoch": 2.769230769230769,
141
+ "grad_norm": 0.07917013019323349,
142
  "learning_rate": 6.153846153846155e-05,
143
+ "loss": 0.0646,
144
  "step": 180
145
  },
146
  {
147
  "epoch": 2.9230769230769234,
148
+ "grad_norm": 0.07372036576271057,
149
  "learning_rate": 5.384615384615385e-05,
150
+ "loss": 0.0452,
151
  "step": 190
152
  },
153
  {
154
  "epoch": 3.076923076923077,
155
+ "grad_norm": 0.0797925740480423,
156
  "learning_rate": 4.615384615384616e-05,
157
+ "loss": 0.031,
158
  "step": 200
159
  },
160
  {
161
  "epoch": 3.076923076923077,
162
+ "eval_accuracy": 0.9849624060150376,
163
+ "eval_loss": 0.0571388304233551,
164
+ "eval_runtime": 1.3229,
165
+ "eval_samples_per_second": 100.536,
166
+ "eval_steps_per_second": 12.85,
167
  "step": 200
168
  },
169
  {
170
  "epoch": 3.230769230769231,
171
+ "grad_norm": 0.08364936709403992,
172
  "learning_rate": 3.846153846153846e-05,
173
+ "loss": 0.0151,
174
  "step": 210
175
  },
176
  {
177
  "epoch": 3.3846153846153846,
178
+ "grad_norm": 0.0659966766834259,
179
  "learning_rate": 3.0769230769230774e-05,
180
+ "loss": 0.013,
181
  "step": 220
182
  },
183
  {
184
  "epoch": 3.5384615384615383,
185
+ "grad_norm": 0.06812237203121185,
186
  "learning_rate": 2.307692307692308e-05,
187
+ "loss": 0.0129,
188
  "step": 230
189
  },
190
  {
191
  "epoch": 3.6923076923076925,
192
+ "grad_norm": 0.06594033539295197,
193
  "learning_rate": 1.5384615384615387e-05,
194
+ "loss": 0.0123,
195
  "step": 240
196
  },
197
  {
198
  "epoch": 3.8461538461538463,
199
+ "grad_norm": 0.06312059611082077,
200
  "learning_rate": 7.692307692307694e-06,
201
+ "loss": 0.0123,
202
  "step": 250
203
  },
204
  {
205
  "epoch": 4.0,
206
+ "grad_norm": 0.0624660886824131,
207
  "learning_rate": 0.0,
208
+ "loss": 0.0121,
209
  "step": 260
210
  },
211
  {
212
  "epoch": 4.0,
213
  "step": 260,
214
  "total_flos": 3.205097416476426e+17,
215
+ "train_loss": 0.12038601376116276,
216
+ "train_runtime": 77.0575,
217
+ "train_samples_per_second": 53.674,
218
+ "train_steps_per_second": 3.374
219
  }
220
  ],
221
  "logging_steps": 10,