Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0730

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0730
File size: 4,285 Bytes 
51061b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9333333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0730/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": 5.074047565460205,
      "learning_rate": 3e-05,
      "loss": 1.2207,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.916,
      "eval_loss": 0.3284676969051361,
      "eval_runtime": 11.4597,
      "eval_samples_per_second": 327.234,
      "eval_steps_per_second": 5.148,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.1721580028533936,
      "learning_rate": 3e-05,
      "loss": 0.2014,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.22639313340187073,
      "eval_runtime": 12.2,
      "eval_samples_per_second": 307.377,
      "eval_steps_per_second": 4.836,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.21025900542736053,
      "learning_rate": 3e-05,
      "loss": 0.0955,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.21491825580596924,
      "eval_runtime": 11.5419,
      "eval_samples_per_second": 324.903,
      "eval_steps_per_second": 5.112,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.11814968287944794,
      "learning_rate": 3e-05,
      "loss": 0.052,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9296,
      "eval_loss": 0.24814409017562866,
      "eval_runtime": 11.5006,
      "eval_samples_per_second": 326.069,
      "eval_steps_per_second": 5.13,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.019923198968172073,
      "learning_rate": 3e-05,
      "loss": 0.0314,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9330666666666667,
      "eval_loss": 0.25124111771583557,
      "eval_runtime": 11.6095,
      "eval_samples_per_second": 323.011,
      "eval_steps_per_second": 5.082,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.024917228147387505,
      "learning_rate": 3e-05,
      "loss": 0.0185,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9296,
      "eval_loss": 0.2741938531398773,
      "eval_runtime": 11.357,
      "eval_samples_per_second": 330.194,
      "eval_steps_per_second": 5.195,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0147,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.2789898216724396,
      "eval_runtime": 11.4802,
      "eval_samples_per_second": 326.649,
      "eval_steps_per_second": 5.139,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.031886909157037735,
      "learning_rate": 3e-05,
      "loss": 0.0122,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9306666666666666,
      "eval_loss": 0.29021015763282776,
      "eval_runtime": 11.5972,
      "eval_samples_per_second": 323.354,
      "eval_steps_per_second": 5.087,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.4433732330799103,
      "learning_rate": 3e-05,
      "loss": 0.0108,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_loss": 0.30287572741508484,
      "eval_runtime": 11.3781,
      "eval_samples_per_second": 329.581,
      "eval_steps_per_second": 5.185,
      "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
}