Hugging Face's logo

Angy309
/
swin-tiny-patch4-window7-224-Lego-v1-3ep

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Angy309 commited on
Commit
3464848
·
verified ·
1 Parent(s): a8c2413

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +13 -0
  2. eval_results.json +8 -0
  3. runs/May13_19-09-27_24cc275b3536/events.out.tfevents.1715633741.24cc275b3536.549.7 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +155 -0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9017857142857143,
4
+ "eval_loss": 0.2857852876186371,
5
+ "eval_runtime": 0.6745,
6
+ "eval_samples_per_second": 166.045,
7
+ "eval_steps_per_second": 5.93,
8
+ "total_flos": 4.6750026057231974e+17,
9
+ "train_loss": 0.9658059327780795,
10
+ "train_runtime": 6347.4478,
11
+ "train_samples_per_second": 2.962,
12
+ "train_steps_per_second": 0.023
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9017857142857143,
4
+ "eval_loss": 0.2857852876186371,
5
+ "eval_runtime": 0.6745,
6
+ "eval_samples_per_second": 166.045,
7
+ "eval_steps_per_second": 5.93
8
+ }
runs/May13_19-09-27_24cc275b3536/events.out.tfevents.1715633741.24cc275b3536.549.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef211cfc5bf6fd9ddf633d33e8bf970b84b05fd7d0cb7e1fddf5f6c0d5c200fc
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 4.6750026057231974e+17,
4
+ "train_loss": 0.9658059327780795,
5
+ "train_runtime": 6347.4478,
6
+ "train_samples_per_second": 2.962,
7
+ "train_steps_per_second": 0.023
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9017857142857143,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-Lego-v1-3ep/checkpoint-147",
4
+ "epoch": 3.0,
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": 0.20408163265306123,
13
+ "grad_norm": 3.9616575241088867,
14
+ "learning_rate": 3.3333333333333335e-05,
15
+ "loss": 2.7824,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.40816326530612246,
20
+ "grad_norm": 5.216483116149902,
21
+ "learning_rate": 4.810606060606061e-05,
22
+ "loss": 2.4565,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.6122448979591837,
27
+ "grad_norm": 8.999798774719238,
28
+ "learning_rate": 4.431818181818182e-05,
29
+ "loss": 1.7257,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.8163265306122449,
34
+ "grad_norm": 13.705337524414062,
35
+ "learning_rate": 4.053030303030303e-05,
36
+ "loss": 1.1779,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_accuracy": 0.75,
42
+ "eval_loss": 0.7035489082336426,
43
+ "eval_runtime": 103.5,
44
+ "eval_samples_per_second": 1.082,
45
+ "eval_steps_per_second": 0.039,
46
+ "step": 49
47
+ },
48
+ {
49
+ "epoch": 1.0204081632653061,
50
+ "grad_norm": 10.42480754852295,
51
+ "learning_rate": 3.6742424242424246e-05,
52
+ "loss": 0.9019,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.2244897959183674,
57
+ "grad_norm": 11.608043670654297,
58
+ "learning_rate": 3.295454545454545e-05,
59
+ "loss": 0.7082,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.4285714285714286,
64
+ "grad_norm": 9.341365814208984,
65
+ "learning_rate": 2.916666666666667e-05,
66
+ "loss": 0.6998,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.6326530612244898,
71
+ "grad_norm": 9.492186546325684,
72
+ "learning_rate": 2.537878787878788e-05,
73
+ "loss": 0.6349,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.836734693877551,
78
+ "grad_norm": 10.111123085021973,
79
+ "learning_rate": 2.1590909090909093e-05,
80
+ "loss": 0.5591,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 2.0,
85
+ "eval_accuracy": 0.8482142857142857,
86
+ "eval_loss": 0.38913723826408386,
87
+ "eval_runtime": 0.7084,
88
+ "eval_samples_per_second": 158.099,
89
+ "eval_steps_per_second": 5.646,
90
+ "step": 98
91
+ },
92
+ {
93
+ "epoch": 2.0408163265306123,
94
+ "grad_norm": 9.370523452758789,
95
+ "learning_rate": 1.7803030303030303e-05,
96
+ "loss": 0.4968,
97
+ "step": 100
98
+ },
99
+ {
100
+ "epoch": 2.2448979591836733,
101
+ "grad_norm": 8.256933212280273,
102
+ "learning_rate": 1.4015151515151515e-05,
103
+ "loss": 0.4329,
104
+ "step": 110
105
+ },
106
+ {
107
+ "epoch": 2.4489795918367347,
108
+ "grad_norm": 11.488386154174805,
109
+ "learning_rate": 1.0227272727272729e-05,
110
+ "loss": 0.4378,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 2.6530612244897958,
115
+ "grad_norm": 9.060242652893066,
116
+ "learning_rate": 6.43939393939394e-06,
117
+ "loss": 0.4341,
118
+ "step": 130
119
+ },
120
+ {
121
+ "epoch": 2.857142857142857,
122
+ "grad_norm": 8.625679016113281,
123
+ "learning_rate": 2.651515151515152e-06,
124
+ "loss": 0.4446,
125
+ "step": 140
126
+ },
127
+ {
128
+ "epoch": 3.0,
129
+ "eval_accuracy": 0.9017857142857143,
130
+ "eval_loss": 0.2857852876186371,
131
+ "eval_runtime": 0.7016,
132
+ "eval_samples_per_second": 159.624,
133
+ "eval_steps_per_second": 5.701,
134
+ "step": 147
135
+ },
136
+ {
137
+ "epoch": 3.0,
138
+ "step": 147,
139
+ "total_flos": 4.6750026057231974e+17,
140
+ "train_loss": 0.9658059327780795,
141
+ "train_runtime": 6347.4478,
142
+ "train_samples_per_second": 2.962,
143
+ "train_steps_per_second": 0.023
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": 4.6750026057231974e+17,
152
+ "train_batch_size": 32,
153
+ "trial_name": null,
154
+ "trial_params": null
155
+ }