Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0798

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0798
File size: 4,448 Bytes 
79dd78d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.94,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0798/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 8.892225558892226e-05,
      "loss": 0.6432,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.916,
      "eval_loss": 0.27572259306907654,
      "eval_runtime": 11.0323,
      "eval_samples_per_second": 339.91,
      "eval_steps_per_second": 5.348,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.053911242634058,
      "learning_rate": 7.781114447781115e-05,
      "loss": 0.1462,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9178666666666667,
      "eval_loss": 0.27192187309265137,
      "eval_runtime": 10.4526,
      "eval_samples_per_second": 358.764,
      "eval_steps_per_second": 5.645,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.6028119325637817,
      "learning_rate": 6.670003336670004e-05,
      "loss": 0.0691,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.928,
      "eval_loss": 0.25854986906051636,
      "eval_runtime": 10.5369,
      "eval_samples_per_second": 355.892,
      "eval_steps_per_second": 5.599,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.019842160865664482,
      "learning_rate": 5.5588922255588925e-05,
      "loss": 0.0299,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9314666666666667,
      "eval_loss": 0.27397575974464417,
      "eval_runtime": 10.9509,
      "eval_samples_per_second": 342.437,
      "eval_steps_per_second": 5.388,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.010537681169807911,
      "learning_rate": 4.447781114447781e-05,
      "loss": 0.0133,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.928,
      "eval_loss": 0.30378469824790955,
      "eval_runtime": 10.4998,
      "eval_samples_per_second": 357.151,
      "eval_steps_per_second": 5.619,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.5650081634521484,
      "learning_rate": 3.33667000333667e-05,
      "loss": 0.0056,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9354666666666667,
      "eval_loss": 0.2910187542438507,
      "eval_runtime": 10.2141,
      "eval_samples_per_second": 367.139,
      "eval_steps_per_second": 5.776,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03130431845784187,
      "learning_rate": 2.225558892225559e-05,
      "loss": 0.0021,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9370666666666667,
      "eval_loss": 0.29938071966171265,
      "eval_runtime": 10.2172,
      "eval_samples_per_second": 367.027,
      "eval_steps_per_second": 5.775,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.013084812089800835,
      "learning_rate": 1.1144477811144478e-05,
      "loss": 0.0011,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.29495272040367126,
      "eval_runtime": 10.5361,
      "eval_samples_per_second": 355.919,
      "eval_steps_per_second": 5.6,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.006984605919569731,
      "learning_rate": 3.3366700033366706e-08,
      "loss": 0.0009,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.94,
      "eval_loss": 0.2896915674209595,
      "eval_runtime": 10.433,
      "eval_samples_per_second": 359.438,
      "eval_steps_per_second": 5.655,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}