Hugging Face's logo

Angy309
/
swin-tiny-patch4-window7-224-finetuned

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Angy309 commited on
Commit
61043be
·
verified ·
1 Parent(s): b46e7ac

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +13 -0
  2. eval_results.json +8 -0
  3. runs/May11_07-54-18_f3912a2b2a6d/events.out.tfevents.1715420091.f3912a2b2a6d.2896.1 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +148 -0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9498432601880877,
4
+ "eval_loss": 0.1711730659008026,
5
+ "eval_runtime": 3.5127,
6
+ "eval_samples_per_second": 181.625,
7
+ "eval_steps_per_second": 5.694,
8
+ "total_flos": 4.282621662590853e+17,
9
+ "train_loss": 0.9712538012751827,
10
+ "train_runtime": 5653.2043,
11
+ "train_samples_per_second": 3.047,
12
+ "train_steps_per_second": 0.024
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9498432601880877,
4
+ "eval_loss": 0.1711730659008026,
5
+ "eval_runtime": 3.5127,
6
+ "eval_samples_per_second": 181.625,
7
+ "eval_steps_per_second": 5.694
8
+ }
runs/May11_07-54-18_f3912a2b2a6d/events.out.tfevents.1715420091.f3912a2b2a6d.2896.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca7e0313d8a8ae595b9cf69b1e62d525b2feda911dff3a001e265ce24427592
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 4.282621662590853e+17,
4
+ "train_loss": 0.9712538012751827,
5
+ "train_runtime": 5653.2043,
6
+ "train_samples_per_second": 3.047,
7
+ "train_steps_per_second": 0.024
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9498432601880877,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned/checkpoint-135",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 135,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2222222222222222,
13
+ "grad_norm": 5.332180976867676,
14
+ "learning_rate": 3.571428571428572e-05,
15
+ "loss": 2.7613,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.4444444444444444,
20
+ "grad_norm": 12.654841423034668,
21
+ "learning_rate": 4.75206611570248e-05,
22
+ "loss": 2.3428,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.6666666666666666,
27
+ "grad_norm": 13.685147285461426,
28
+ "learning_rate": 4.338842975206612e-05,
29
+ "loss": 1.6575,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.8888888888888888,
34
+ "grad_norm": 11.329548835754395,
35
+ "learning_rate": 3.925619834710744e-05,
36
+ "loss": 1.1146,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_accuracy": 0.7774294670846394,
42
+ "eval_loss": 0.6721618175506592,
43
+ "eval_runtime": 586.524,
44
+ "eval_samples_per_second": 1.088,
45
+ "eval_steps_per_second": 0.034,
46
+ "step": 45
47
+ },
48
+ {
49
+ "epoch": 1.1111111111111112,
50
+ "grad_norm": 10.730902671813965,
51
+ "learning_rate": 3.512396694214876e-05,
52
+ "loss": 0.8703,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.3333333333333333,
57
+ "grad_norm": 9.959417343139648,
58
+ "learning_rate": 3.099173553719008e-05,
59
+ "loss": 0.6665,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.5555555555555556,
64
+ "grad_norm": 8.136271476745605,
65
+ "learning_rate": 2.6859504132231405e-05,
66
+ "loss": 0.6139,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.7777777777777777,
71
+ "grad_norm": 7.427969455718994,
72
+ "learning_rate": 2.272727272727273e-05,
73
+ "loss": 0.5748,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 2.0,
78
+ "grad_norm": 8.851130485534668,
79
+ "learning_rate": 1.859504132231405e-05,
80
+ "loss": 0.5419,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 2.0,
85
+ "eval_accuracy": 0.9341692789968652,
86
+ "eval_loss": 0.2221757173538208,
87
+ "eval_runtime": 3.3094,
88
+ "eval_samples_per_second": 192.787,
89
+ "eval_steps_per_second": 6.043,
90
+ "step": 90
91
+ },
92
+ {
93
+ "epoch": 2.2222222222222223,
94
+ "grad_norm": 9.288217544555664,
95
+ "learning_rate": 1.4462809917355372e-05,
96
+ "loss": 0.4968,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.4444444444444446,
101
+ "grad_norm": 12.425986289978027,
102
+ "learning_rate": 1.0330578512396695e-05,
103
+ "loss": 0.4119,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.6666666666666665,
108
+ "grad_norm": 7.838353157043457,
109
+ "learning_rate": 6.198347107438017e-06,
110
+ "loss": 0.4118,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 2.888888888888889,
115
+ "grad_norm": 6.44113826751709,
116
+ "learning_rate": 2.066115702479339e-06,
117
+ "loss": 0.4282,
118
+ "step": 130
119
+ },
120
+ {
121
+ "epoch": 3.0,
122
+ "eval_accuracy": 0.9498432601880877,
123
+ "eval_loss": 0.1711730659008026,
124
+ "eval_runtime": 3.4263,
125
+ "eval_samples_per_second": 186.204,
126
+ "eval_steps_per_second": 5.837,
127
+ "step": 135
128
+ },
129
+ {
130
+ "epoch": 3.0,
131
+ "step": 135,
132
+ "total_flos": 4.282621662590853e+17,
133
+ "train_loss": 0.9712538012751827,
134
+ "train_runtime": 5653.2043,
135
+ "train_samples_per_second": 3.047,
136
+ "train_steps_per_second": 0.024
137
+ }
138
+ ],
139
+ "logging_steps": 10,
140
+ "max_steps": 135,
141
+ "num_input_tokens_seen": 0,
142
+ "num_train_epochs": 3,
143
+ "save_steps": 500,
144
+ "total_flos": 4.282621662590853e+17,
145
+ "train_batch_size": 32,
146
+ "trial_name": null,
147
+ "trial_params": null
148
+ }