Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0261

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0261
File size: 3,944 Bytes 
e879afc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8402666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0261/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": 0.21289286017417908,
      "learning_rate": 0.0005,
      "loss": 0.7565,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8109333333333333,
      "eval_loss": 0.6438400745391846,
      "eval_runtime": 11.0434,
      "eval_samples_per_second": 339.568,
      "eval_steps_per_second": 5.343,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.77164649963379,
      "learning_rate": 0.0005,
      "loss": 0.4312,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8346666666666667,
      "eval_loss": 0.581412136554718,
      "eval_runtime": 11.3783,
      "eval_samples_per_second": 329.574,
      "eval_steps_per_second": 5.185,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.604055881500244,
      "learning_rate": 0.0005,
      "loss": 0.3331,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8181333333333334,
      "eval_loss": 0.6724151968955994,
      "eval_runtime": 12.089,
      "eval_samples_per_second": 310.2,
      "eval_steps_per_second": 4.88,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.240381240844727,
      "learning_rate": 0.0005,
      "loss": 0.2854,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8096,
      "eval_loss": 0.6944108605384827,
      "eval_runtime": 11.3621,
      "eval_samples_per_second": 330.046,
      "eval_steps_per_second": 5.193,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 0.2448,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8344,
      "eval_loss": 0.593360424041748,
      "eval_runtime": 11.2485,
      "eval_samples_per_second": 333.378,
      "eval_steps_per_second": 5.245,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.3359733819961548,
      "learning_rate": 0.0005,
      "loss": 0.2086,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8074666666666667,
      "eval_loss": 0.7485321164131165,
      "eval_runtime": 11.2603,
      "eval_samples_per_second": 333.027,
      "eval_steps_per_second": 5.24,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.4460902214050293,
      "learning_rate": 0.0005,
      "loss": 0.1973,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8242666666666667,
      "eval_loss": 0.6548503637313843,
      "eval_runtime": 10.6546,
      "eval_samples_per_second": 351.96,
      "eval_steps_per_second": 5.538,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 20.645042419433594,
      "learning_rate": 0.0005,
      "loss": 0.1818,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.6299357414245605,
      "eval_runtime": 10.6878,
      "eval_samples_per_second": 350.866,
      "eval_steps_per_second": 5.52,
      "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
}