Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0642

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0642
File size: 4,065 Bytes 
4e97632
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9613333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0642/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": 0.2910105884075165,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.8311,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9418666666666666,
      "eval_loss": 0.2433604598045349,
      "eval_runtime": 13.2664,
      "eval_samples_per_second": 282.67,
      "eval_steps_per_second": 4.447,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.11035412549972534,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.1197,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9482666666666667,
      "eval_loss": 0.1882043331861496,
      "eval_runtime": 12.7847,
      "eval_samples_per_second": 293.318,
      "eval_steps_per_second": 4.615,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.024116288870573044,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.0498,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9512,
      "eval_loss": 0.1856408566236496,
      "eval_runtime": 13.0866,
      "eval_samples_per_second": 286.553,
      "eval_steps_per_second": 4.508,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.878389298915863,
      "learning_rate": 2.5e-05,
      "loss": 0.0235,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9514666666666667,
      "eval_loss": 0.17935959994792938,
      "eval_runtime": 13.0185,
      "eval_samples_per_second": 288.052,
      "eval_steps_per_second": 4.532,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.08202634006738663,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.0094,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9538666666666666,
      "eval_loss": 0.18147802352905273,
      "eval_runtime": 12.8685,
      "eval_samples_per_second": 291.409,
      "eval_steps_per_second": 4.585,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01814800314605236,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0043,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9584,
      "eval_loss": 0.17454007267951965,
      "eval_runtime": 13.1547,
      "eval_samples_per_second": 285.068,
      "eval_steps_per_second": 4.485,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.91430998468726e-06,
      "loss": 0.0031,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9570666666666666,
      "eval_loss": 0.16638565063476562,
      "eval_runtime": 13.1128,
      "eval_samples_per_second": 285.98,
      "eval_steps_per_second": 4.499,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.2902815639972687,
      "learning_rate": 1.7383661915504334e-11,
      "loss": 0.0026,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9613333333333334,
      "eval_loss": 0.16239814460277557,
      "eval_runtime": 13.1034,
      "eval_samples_per_second": 286.184,
      "eval_steps_per_second": 4.503,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}