Hugging Face's logo

phonghoccode
/
results

Image Classification
Transformers
TensorBoard
Safetensors
vit
vision
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
phonghoccode commited on
Commit
92fa781
•
1 Parent(s): 7189f5d

End of training

Browse files
Files changed (6) hide show
  1. README.md +2 -0
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. runs/Jun30_02-20-27_05003a8a7fe6/events.out.tfevents.1719714427.05003a8a7fe6.136.1 +3 -0
  5. train_results.json +8 -0
  6. trainer_state.json +206 -0
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
 
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
+ - image-classification
6
+ - vision
7
  - generated_from_trainer
8
  datasets:
9
  - imagefolder
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9402390438247012,
4
+ "eval_loss": 0.2654401361942291,
5
+ "eval_runtime": 5.2063,
6
+ "eval_samples_per_second": 48.211,
7
+ "eval_steps_per_second": 0.768,
8
+ "total_flos": 8.264816981535744e+17,
9
+ "train_loss": 0.3976527817109052,
10
+ "train_runtime": 377.5007,
11
+ "train_samples_per_second": 28.252,
12
+ "train_steps_per_second": 0.45
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9402390438247012,
4
+ "eval_loss": 0.2654401361942291,
5
+ "eval_runtime": 5.2063,
6
+ "eval_samples_per_second": 48.211,
7
+ "eval_steps_per_second": 0.768
8
+ }
runs/Jun30_02-20-27_05003a8a7fe6/events.out.tfevents.1719714427.05003a8a7fe6.136.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9b25a8404b8e9898bc82bbc7a725f27cda485553eb3279d0853f45c6a86d4f
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 8.264816981535744e+17,
4
+ "train_loss": 0.3976527817109052,
5
+ "train_runtime": 377.5007,
6
+ "train_samples_per_second": 28.252,
7
+ "train_steps_per_second": 0.45
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2654401361942291,
3
+ "best_model_checkpoint": "/kaggle/working/results/checkpoint-170",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 170,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.29411764705882354,
13
+ "grad_norm": 1.7904845476150513,
14
+ "learning_rate": 4.705882352941177e-05,
15
+ "loss": 1.3311,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.5882352941176471,
20
+ "grad_norm": 1.4475995302200317,
21
+ "learning_rate": 4.411764705882353e-05,
22
+ "loss": 0.7478,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.8823529411764706,
27
+ "grad_norm": 1.0543155670166016,
28
+ "learning_rate": 4.11764705882353e-05,
29
+ "loss": 0.5724,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "eval_accuracy": 0.9163346613545816,
35
+ "eval_loss": 0.42589500546455383,
36
+ "eval_runtime": 5.1988,
37
+ "eval_samples_per_second": 48.28,
38
+ "eval_steps_per_second": 0.769,
39
+ "step": 34
40
+ },
41
+ {
42
+ "epoch": 1.1764705882352942,
43
+ "grad_norm": 0.9727240204811096,
44
+ "learning_rate": 3.8235294117647055e-05,
45
+ "loss": 0.4738,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 1.4705882352941178,
50
+ "grad_norm": 0.6961530447006226,
51
+ "learning_rate": 3.529411764705883e-05,
52
+ "loss": 0.4334,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.7647058823529411,
57
+ "grad_norm": 0.9150127172470093,
58
+ "learning_rate": 3.235294117647059e-05,
59
+ "loss": 0.3558,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 2.0,
64
+ "eval_accuracy": 0.9362549800796812,
65
+ "eval_loss": 0.3115582764148712,
66
+ "eval_runtime": 5.2552,
67
+ "eval_samples_per_second": 47.762,
68
+ "eval_steps_per_second": 0.761,
69
+ "step": 68
70
+ },
71
+ {
72
+ "epoch": 2.0588235294117645,
73
+ "grad_norm": 0.8191739916801453,
74
+ "learning_rate": 2.9411764705882354e-05,
75
+ "loss": 0.3313,
76
+ "step": 70
77
+ },
78
+ {
79
+ "epoch": 2.3529411764705883,
80
+ "grad_norm": 0.8822425007820129,
81
+ "learning_rate": 2.647058823529412e-05,
82
+ "loss": 0.3025,
83
+ "step": 80
84
+ },
85
+ {
86
+ "epoch": 2.6470588235294117,
87
+ "grad_norm": 1.1780915260314941,
88
+ "learning_rate": 2.3529411764705884e-05,
89
+ "loss": 0.2882,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 2.9411764705882355,
94
+ "grad_norm": 1.081735610961914,
95
+ "learning_rate": 2.058823529411765e-05,
96
+ "loss": 0.2732,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 3.0,
101
+ "eval_accuracy": 0.9362549800796812,
102
+ "eval_loss": 0.28424072265625,
103
+ "eval_runtime": 5.1718,
104
+ "eval_samples_per_second": 48.532,
105
+ "eval_steps_per_second": 0.773,
106
+ "step": 102
107
+ },
108
+ {
109
+ "epoch": 3.235294117647059,
110
+ "grad_norm": 0.8298177123069763,
111
+ "learning_rate": 1.7647058823529414e-05,
112
+ "loss": 0.2513,
113
+ "step": 110
114
+ },
115
+ {
116
+ "epoch": 3.5294117647058822,
117
+ "grad_norm": 0.933785080909729,
118
+ "learning_rate": 1.4705882352941177e-05,
119
+ "loss": 0.2497,
120
+ "step": 120
121
+ },
122
+ {
123
+ "epoch": 3.8235294117647056,
124
+ "grad_norm": 0.7405449748039246,
125
+ "learning_rate": 1.1764705882352942e-05,
126
+ "loss": 0.2286,
127
+ "step": 130
128
+ },
129
+ {
130
+ "epoch": 4.0,
131
+ "eval_accuracy": 0.9402390438247012,
132
+ "eval_loss": 0.269024133682251,
133
+ "eval_runtime": 5.2408,
134
+ "eval_samples_per_second": 47.894,
135
+ "eval_steps_per_second": 0.763,
136
+ "step": 136
137
+ },
138
+ {
139
+ "epoch": 4.117647058823529,
140
+ "grad_norm": 0.9281182289123535,
141
+ "learning_rate": 8.823529411764707e-06,
142
+ "loss": 0.2377,
143
+ "step": 140
144
+ },
145
+ {
146
+ "epoch": 4.411764705882353,
147
+ "grad_norm": 1.4719483852386475,
148
+ "learning_rate": 5.882352941176471e-06,
149
+ "loss": 0.2671,
150
+ "step": 150
151
+ },
152
+ {
153
+ "epoch": 4.705882352941177,
154
+ "grad_norm": 0.7358911633491516,
155
+ "learning_rate": 2.9411764705882355e-06,
156
+ "loss": 0.218,
157
+ "step": 160
158
+ },
159
+ {
160
+ "epoch": 5.0,
161
+ "grad_norm": 1.2096456289291382,
162
+ "learning_rate": 0.0,
163
+ "loss": 0.1984,
164
+ "step": 170
165
+ },
166
+ {
167
+ "epoch": 5.0,
168
+ "eval_accuracy": 0.9402390438247012,
169
+ "eval_loss": 0.2654401361942291,
170
+ "eval_runtime": 5.4015,
171
+ "eval_samples_per_second": 46.468,
172
+ "eval_steps_per_second": 0.741,
173
+ "step": 170
174
+ },
175
+ {
176
+ "epoch": 5.0,
177
+ "step": 170,
178
+ "total_flos": 8.264816981535744e+17,
179
+ "train_loss": 0.3976527817109052,
180
+ "train_runtime": 377.5007,
181
+ "train_samples_per_second": 28.252,
182
+ "train_steps_per_second": 0.45
183
+ }
184
+ ],
185
+ "logging_steps": 10,
186
+ "max_steps": 170,
187
+ "num_input_tokens_seen": 0,
188
+ "num_train_epochs": 5,
189
+ "save_steps": 500,
190
+ "stateful_callbacks": {
191
+ "TrainerControl": {
192
+ "args": {
193
+ "should_epoch_stop": false,
194
+ "should_evaluate": false,
195
+ "should_log": false,
196
+ "should_save": true,
197
+ "should_training_stop": true
198
+ },
199
+ "attributes": {}
200
+ }
201
+ },
202
+ "total_flos": 8.264816981535744e+17,
203
+ "train_batch_size": 64,
204
+ "trial_name": null,
205
+ "trial_params": null
206
+ }