Hugging Face's logo

griffio
/
vit-large-patch16-224-in21k-dungeon-geo-morphs-0-4-30Nov24-003

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
griffio commited on
Commit
becf38d
·
verified ·
1 Parent(s): 1f01a02

Model save

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +170 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 31.90909090909091,
3
+ "total_flos": 7.012786101918106e+17,
4
+ "train_loss": 0.2615024119615555,
5
+ "train_runtime": 561.0998,
6
+ "train_samples_per_second": 5.846,
7
+ "train_steps_per_second": 0.143
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 31.90909090909091,
3
+ "total_flos": 7.012786101918106e+17,
4
+ "train_loss": 0.2615024119615555,
5
+ "train_runtime": 561.0998,
6
+ "train_samples_per_second": 5.846,
7
+ "train_steps_per_second": 0.143
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9589285714285715,
3
+ "best_model_checkpoint": "vit-large-patch16-224-in21k-dungeon-geo-morphs-0-4-30Nov24-003/checkpoint-50",
4
+ "epoch": 31.90909090909091,
5
+ "eval_steps": 10,
6
+ "global_step": 80,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.909090909090909,
13
+ "grad_norm": 16.135948181152344,
14
+ "learning_rate": 1.9444444444444445e-05,
15
+ "loss": 1.3682,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 3.909090909090909,
20
+ "eval_accuracy": 0.825,
21
+ "eval_loss": 1.0376439094543457,
22
+ "eval_runtime": 7.5608,
23
+ "eval_samples_per_second": 74.066,
24
+ "eval_steps_per_second": 9.258,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 7.909090909090909,
29
+ "grad_norm": 7.783586025238037,
30
+ "learning_rate": 1.6944444444444446e-05,
31
+ "loss": 0.5281,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 7.909090909090909,
36
+ "eval_accuracy": 0.9196428571428571,
37
+ "eval_loss": 0.530949592590332,
38
+ "eval_runtime": 7.6225,
39
+ "eval_samples_per_second": 73.467,
40
+ "eval_steps_per_second": 9.183,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 11.909090909090908,
45
+ "grad_norm": 4.47883939743042,
46
+ "learning_rate": 1.416666666666667e-05,
47
+ "loss": 0.1424,
48
+ "step": 30
49
+ },
50
+ {
51
+ "epoch": 11.909090909090908,
52
+ "eval_accuracy": 0.9375,
53
+ "eval_loss": 0.2757301926612854,
54
+ "eval_runtime": 8.417,
55
+ "eval_samples_per_second": 66.532,
56
+ "eval_steps_per_second": 8.316,
57
+ "step": 30
58
+ },
59
+ {
60
+ "epoch": 15.909090909090908,
61
+ "grad_norm": 0.6547029614448547,
62
+ "learning_rate": 1.138888888888889e-05,
63
+ "loss": 0.033,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 15.909090909090908,
68
+ "eval_accuracy": 0.9482142857142857,
69
+ "eval_loss": 0.16814185678958893,
70
+ "eval_runtime": 7.3224,
71
+ "eval_samples_per_second": 76.478,
72
+ "eval_steps_per_second": 9.56,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 19.90909090909091,
77
+ "grad_norm": 0.3083936274051666,
78
+ "learning_rate": 8.611111111111112e-06,
79
+ "loss": 0.0093,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 19.90909090909091,
84
+ "eval_accuracy": 0.9589285714285715,
85
+ "eval_loss": 0.13735760748386383,
86
+ "eval_runtime": 7.5693,
87
+ "eval_samples_per_second": 73.983,
88
+ "eval_steps_per_second": 9.248,
89
+ "step": 50
90
+ },
91
+ {
92
+ "epoch": 23.90909090909091,
93
+ "grad_norm": 0.14518193900585175,
94
+ "learning_rate": 5.833333333333334e-06,
95
+ "loss": 0.0046,
96
+ "step": 60
97
+ },
98
+ {
99
+ "epoch": 23.90909090909091,
100
+ "eval_accuracy": 0.9589285714285715,
101
+ "eval_loss": 0.12884944677352905,
102
+ "eval_runtime": 7.9661,
103
+ "eval_samples_per_second": 70.298,
104
+ "eval_steps_per_second": 8.787,
105
+ "step": 60
106
+ },
107
+ {
108
+ "epoch": 27.90909090909091,
109
+ "grad_norm": 0.10925909131765366,
110
+ "learning_rate": 3.055555555555556e-06,
111
+ "loss": 0.0034,
112
+ "step": 70
113
+ },
114
+ {
115
+ "epoch": 27.90909090909091,
116
+ "eval_accuracy": 0.9571428571428572,
117
+ "eval_loss": 0.12211893498897552,
118
+ "eval_runtime": 7.4941,
119
+ "eval_samples_per_second": 74.725,
120
+ "eval_steps_per_second": 9.341,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 31.90909090909091,
125
+ "grad_norm": 0.09304070472717285,
126
+ "learning_rate": 2.7777777777777776e-07,
127
+ "loss": 0.003,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 31.90909090909091,
132
+ "eval_accuracy": 0.9571428571428572,
133
+ "eval_loss": 0.12084805965423584,
134
+ "eval_runtime": 7.2756,
135
+ "eval_samples_per_second": 76.97,
136
+ "eval_steps_per_second": 9.621,
137
+ "step": 80
138
+ },
139
+ {
140
+ "epoch": 31.90909090909091,
141
+ "step": 80,
142
+ "total_flos": 7.012786101918106e+17,
143
+ "train_loss": 0.2615024119615555,
144
+ "train_runtime": 561.0998,
145
+ "train_samples_per_second": 5.846,
146
+ "train_steps_per_second": 0.143
147
+ }
148
+ ],
149
+ "logging_steps": 10,
150
+ "max_steps": 80,
151
+ "num_input_tokens_seen": 0,
152
+ "num_train_epochs": 40,
153
+ "save_steps": 10,
154
+ "stateful_callbacks": {
155
+ "TrainerControl": {
156
+ "args": {
157
+ "should_epoch_stop": false,
158
+ "should_evaluate": false,
159
+ "should_log": false,
160
+ "should_save": true,
161
+ "should_training_stop": true
162
+ },
163
+ "attributes": {}
164
+ }
165
+ },
166
+ "total_flos": 7.012786101918106e+17,
167
+ "train_batch_size": 8,
168
+ "trial_name": null,
169
+ "trial_params": null
170
+ }