Hugging Face's logo

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

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
zabir735 commited on
Commit
c657bea
•
1 Parent(s): e9b9f69

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 +155 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.984771573604061,
3
+ "total_flos": 1.1692257218946662e+17,
4
+ "train_loss": 0.1783457891065247,
5
+ "train_runtime": 84.8256,
6
+ "train_samples_per_second": 55.738,
7
+ "train_steps_per_second": 1.733
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.984771573604061,
3
+ "total_flos": 1.1692257218946662e+17,
4
+ "train_loss": 0.1783457891065247,
5
+ "train_runtime": 84.8256,
6
+ "train_samples_per_second": 55.738,
7
+ "train_steps_per_second": 1.733
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9715909090909091,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-batch8-nocrop/checkpoint-147",
4
+ "epoch": 2.984771573604061,
5
+ "eval_steps": 500,
6
+ "global_step": 147,
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": 6.709445953369141,
14
+ "learning_rate": 3.3333333333333335e-05,
15
+ "loss": 0.6831,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.40609137055837563,
20
+ "grad_norm": 36.66501235961914,
21
+ "learning_rate": 4.810606060606061e-05,
22
+ "loss": 0.5802,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.6091370558375635,
27
+ "grad_norm": 7.574514865875244,
28
+ "learning_rate": 4.431818181818182e-05,
29
+ "loss": 0.3748,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.8121827411167513,
34
+ "grad_norm": 12.18085765838623,
35
+ "learning_rate": 4.053030303030303e-05,
36
+ "loss": 0.2052,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.9949238578680203,
41
+ "eval_accuracy": 0.9602272727272727,
42
+ "eval_loss": 0.15112267434597015,
43
+ "eval_runtime": 1.4305,
44
+ "eval_samples_per_second": 123.032,
45
+ "eval_steps_per_second": 15.379,
46
+ "step": 49
47
+ },
48
+ {
49
+ "epoch": 1.015228426395939,
50
+ "grad_norm": 8.17941665649414,
51
+ "learning_rate": 3.6742424242424246e-05,
52
+ "loss": 0.1755,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.218274111675127,
57
+ "grad_norm": 7.0626115798950195,
58
+ "learning_rate": 3.295454545454545e-05,
59
+ "loss": 0.0786,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.4213197969543148,
64
+ "grad_norm": 25.362876892089844,
65
+ "learning_rate": 2.916666666666667e-05,
66
+ "loss": 0.1441,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.6243654822335025,
71
+ "grad_norm": 15.33166790008545,
72
+ "learning_rate": 2.537878787878788e-05,
73
+ "loss": 0.0825,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.8274111675126905,
78
+ "grad_norm": 2.483710527420044,
79
+ "learning_rate": 2.1590909090909093e-05,
80
+ "loss": 0.0852,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 1.9898477157360406,
85
+ "eval_accuracy": 0.9488636363636364,
86
+ "eval_loss": 0.1786985695362091,
87
+ "eval_runtime": 1.4267,
88
+ "eval_samples_per_second": 123.365,
89
+ "eval_steps_per_second": 15.421,
90
+ "step": 98
91
+ },
92
+ {
93
+ "epoch": 2.030456852791878,
94
+ "grad_norm": 23.29215431213379,
95
+ "learning_rate": 1.7803030303030303e-05,
96
+ "loss": 0.0657,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.233502538071066,
101
+ "grad_norm": 4.370492458343506,
102
+ "learning_rate": 1.4015151515151515e-05,
103
+ "loss": 0.0307,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.436548223350254,
108
+ "grad_norm": 9.500088691711426,
109
+ "learning_rate": 1.0227272727272729e-05,
110
+ "loss": 0.0276,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 2.6395939086294415,
115
+ "grad_norm": 6.448863506317139,
116
+ "learning_rate": 6.43939393939394e-06,
117
+ "loss": 0.0273,
118
+ "step": 130
119
+ },
120
+ {
121
+ "epoch": 2.8426395939086295,
122
+ "grad_norm": 7.503269672393799,
123
+ "learning_rate": 2.651515151515152e-06,
124
+ "loss": 0.0336,
125
+ "step": 140
126
+ },
127
+ {
128
+ "epoch": 2.984771573604061,
129
+ "eval_accuracy": 0.9715909090909091,
130
+ "eval_loss": 0.09903481602668762,
131
+ "eval_runtime": 1.4469,
132
+ "eval_samples_per_second": 121.636,
133
+ "eval_steps_per_second": 15.205,
134
+ "step": 147
135
+ },
136
+ {
137
+ "epoch": 2.984771573604061,
138
+ "step": 147,
139
+ "total_flos": 1.1692257218946662e+17,
140
+ "train_loss": 0.1783457891065247,
141
+ "train_runtime": 84.8256,
142
+ "train_samples_per_second": 55.738,
143
+ "train_steps_per_second": 1.733
144
+ }
145
+ ],
146
+ "logging_steps": 10,
147
+ "max_steps": 147,
148
+ "num_input_tokens_seen": 0,
149
+ "num_train_epochs": 3,
150
+ "save_steps": 500,
151
+ "total_flos": 1.1692257218946662e+17,
152
+ "train_batch_size": 8,
153
+ "trial_name": null,
154
+ "trial_params": null
155
+ }