Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0487

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0487
File size: 4,071 Bytes 
b9e84e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.9394666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0487/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.7975496053695679,
      "learning_rate": 6.788924172750679e-05,
      "loss": 0.706,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9176,
      "eval_loss": 0.2901247441768646,
      "eval_runtime": 6.4063,
      "eval_samples_per_second": 585.363,
      "eval_steps_per_second": 9.21,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.29411831498146057,
      "learning_rate": 6.181155550916422e-05,
      "loss": 0.1376,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9226666666666666,
      "eval_loss": 0.2622464597225189,
      "eval_runtime": 6.4175,
      "eval_samples_per_second": 584.344,
      "eval_steps_per_second": 9.194,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.02292746491730213,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.0596,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9261333333333334,
      "eval_loss": 0.2584249973297119,
      "eval_runtime": 6.3006,
      "eval_samples_per_second": 595.181,
      "eval_steps_per_second": 9.364,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.02821717970073223,
      "learning_rate": 4.1077686218342566e-05,
      "loss": 0.0254,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.2813774645328522,
      "eval_runtime": 6.235,
      "eval_samples_per_second": 601.443,
      "eval_steps_per_second": 9.463,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1251145899295807,
      "learning_rate": 2.8922313781657438e-05,
      "loss": 0.0103,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9341333333333334,
      "eval_loss": 0.26139748096466064,
      "eval_runtime": 7.3239,
      "eval_samples_per_second": 512.025,
      "eval_steps_per_second": 8.056,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.05425437167286873,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0028,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.27179527282714844,
      "eval_runtime": 6.4528,
      "eval_samples_per_second": 581.147,
      "eval_steps_per_second": 9.143,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 8.212042196399656e-06,
      "loss": 0.0017,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.2657235562801361,
      "eval_runtime": 6.6982,
      "eval_samples_per_second": 559.853,
      "eval_steps_per_second": 8.808,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.04576840251684189,
      "learning_rate": 2.1233245810799825e-06,
      "loss": 0.0016,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.2715781331062317,
      "eval_runtime": 6.2783,
      "eval_samples_per_second": 597.298,
      "eval_steps_per_second": 9.397,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}