Hugging Face's logo

NekoFi
/
portrait_cosu_exp5

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
NekoFi commited on
Commit
5b159cc
•
1 Parent(s): 45f9205

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 +158 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.902439024390244,
3
+ "total_flos": 5.787149236001833e+17,
4
+ "train_loss": 0.2959394633769989,
5
+ "train_runtime": 442.5785,
6
+ "train_samples_per_second": 5.857,
7
+ "train_steps_per_second": 0.09
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.902439024390244,
3
+ "total_flos": 5.787149236001833e+17,
4
+ "train_loss": 0.2959394633769989,
5
+ "train_runtime": 442.5785,
6
+ "train_samples_per_second": 5.857,
7
+ "train_steps_per_second": 0.09
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9583333333333334,
3
+ "best_model_checkpoint": "portrait_cosu_exp5/checkpoint-40",
4
+ "epoch": 3.902439024390244,
5
+ "eval_steps": 500,
6
+ "global_step": 40,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.975609756097561,
13
+ "grad_norm": 13.03514289855957,
14
+ "learning_rate": 4.166666666666667e-05,
15
+ "loss": 0.3966,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.975609756097561,
20
+ "eval_accuracy": 0.8611111111111112,
21
+ "eval_confusion_matrix": [
22
+ [
23
+ 50,
24
+ 1
25
+ ],
26
+ [
27
+ 9,
28
+ 12
29
+ ]
30
+ ],
31
+ "eval_f1": 0.8498217468805704,
32
+ "eval_loss": 0.30243051052093506,
33
+ "eval_precision": 0.8695132551064755,
34
+ "eval_recall": 0.8611111111111112,
35
+ "eval_runtime": 5.8713,
36
+ "eval_samples_per_second": 12.263,
37
+ "eval_steps_per_second": 0.852,
38
+ "step": 10
39
+ },
40
+ {
41
+ "epoch": 1.951219512195122,
42
+ "grad_norm": 18.37648582458496,
43
+ "learning_rate": 2.777777777777778e-05,
44
+ "loss": 0.3486,
45
+ "step": 20
46
+ },
47
+ {
48
+ "epoch": 1.951219512195122,
49
+ "eval_accuracy": 0.8333333333333334,
50
+ "eval_confusion_matrix": [
51
+ [
52
+ 50,
53
+ 1
54
+ ],
55
+ [
56
+ 11,
57
+ 10
58
+ ]
59
+ ],
60
+ "eval_f1": 0.8147321428571428,
61
+ "eval_loss": 0.3285925090312958,
62
+ "eval_precision": 0.84575260804769,
63
+ "eval_recall": 0.8333333333333334,
64
+ "eval_runtime": 5.962,
65
+ "eval_samples_per_second": 12.077,
66
+ "eval_steps_per_second": 0.839,
67
+ "step": 20
68
+ },
69
+ {
70
+ "epoch": 2.926829268292683,
71
+ "grad_norm": 4.450592517852783,
72
+ "learning_rate": 1.388888888888889e-05,
73
+ "loss": 0.2347,
74
+ "step": 30
75
+ },
76
+ {
77
+ "epoch": 2.926829268292683,
78
+ "eval_accuracy": 0.9444444444444444,
79
+ "eval_confusion_matrix": [
80
+ [
81
+ 50,
82
+ 1
83
+ ],
84
+ [
85
+ 3,
86
+ 18
87
+ ]
88
+ ],
89
+ "eval_f1": 0.9435897435897436,
90
+ "eval_loss": 0.17685942351818085,
91
+ "eval_precision": 0.9445547831843761,
92
+ "eval_recall": 0.9444444444444444,
93
+ "eval_runtime": 5.6367,
94
+ "eval_samples_per_second": 12.773,
95
+ "eval_steps_per_second": 0.887,
96
+ "step": 30
97
+ },
98
+ {
99
+ "epoch": 3.902439024390244,
100
+ "grad_norm": 6.283059597015381,
101
+ "learning_rate": 0.0,
102
+ "loss": 0.2039,
103
+ "step": 40
104
+ },
105
+ {
106
+ "epoch": 3.902439024390244,
107
+ "eval_accuracy": 0.9583333333333334,
108
+ "eval_confusion_matrix": [
109
+ [
110
+ 50,
111
+ 1
112
+ ],
113
+ [
114
+ 2,
115
+ 19
116
+ ]
117
+ ],
118
+ "eval_f1": 0.9580274686242009,
119
+ "eval_loss": 0.16026876866817474,
120
+ "eval_precision": 0.9581730769230768,
121
+ "eval_recall": 0.9583333333333334,
122
+ "eval_runtime": 5.4865,
123
+ "eval_samples_per_second": 13.123,
124
+ "eval_steps_per_second": 0.911,
125
+ "step": 40
126
+ },
127
+ {
128
+ "epoch": 3.902439024390244,
129
+ "step": 40,
130
+ "total_flos": 5.787149236001833e+17,
131
+ "train_loss": 0.2959394633769989,
132
+ "train_runtime": 442.5785,
133
+ "train_samples_per_second": 5.857,
134
+ "train_steps_per_second": 0.09
135
+ }
136
+ ],
137
+ "logging_steps": 10,
138
+ "max_steps": 40,
139
+ "num_input_tokens_seen": 0,
140
+ "num_train_epochs": 4,
141
+ "save_steps": 500,
142
+ "stateful_callbacks": {
143
+ "TrainerControl": {
144
+ "args": {
145
+ "should_epoch_stop": false,
146
+ "should_evaluate": false,
147
+ "should_log": false,
148
+ "should_save": true,
149
+ "should_training_stop": true
150
+ },
151
+ "attributes": {}
152
+ }
153
+ },
154
+ "total_flos": 5.787149236001833e+17,
155
+ "train_batch_size": 16,
156
+ "trial_name": null,
157
+ "trial_params": null
158
+ }