Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0533

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0533
File size: 4,034 Bytes 
a208649
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_0533/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": 0.3819980323314667,
      "learning_rate": 7.875e-05,
      "loss": 0.691,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.908,
      "eval_loss": 0.3238830268383026,
      "eval_runtime": 10.893,
      "eval_samples_per_second": 344.257,
      "eval_steps_per_second": 5.416,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.18436698615550995,
      "learning_rate": 6.75e-05,
      "loss": 0.1591,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9245333333333333,
      "eval_loss": 0.25347280502319336,
      "eval_runtime": 10.8899,
      "eval_samples_per_second": 344.356,
      "eval_steps_per_second": 5.418,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 5.628378378378378e-05,
      "loss": 0.0765,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9256,
      "eval_loss": 0.2824830710887909,
      "eval_runtime": 11.2663,
      "eval_samples_per_second": 332.85,
      "eval_steps_per_second": 5.237,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.16674105823040009,
      "learning_rate": 4.503378378378379e-05,
      "loss": 0.0337,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9250666666666667,
      "eval_loss": 0.30557408928871155,
      "eval_runtime": 11.3105,
      "eval_samples_per_second": 331.55,
      "eval_steps_per_second": 5.216,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.07897784560918808,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 0.0192,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.2793754041194916,
      "eval_runtime": 10.858,
      "eval_samples_per_second": 345.368,
      "eval_steps_per_second": 5.434,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.007504582870751619,
      "learning_rate": 2.2533783783783782e-05,
      "loss": 0.0083,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9352,
      "eval_loss": 0.2799282968044281,
      "eval_runtime": 10.7896,
      "eval_samples_per_second": 347.558,
      "eval_steps_per_second": 5.468,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.007476204540580511,
      "learning_rate": 1.1283783783783785e-05,
      "loss": 0.0037,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9392,
      "eval_loss": 0.2660500109195709,
      "eval_runtime": 10.6873,
      "eval_samples_per_second": 350.883,
      "eval_steps_per_second": 5.521,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.005210889503359795,
      "learning_rate": 3.3783783783783786e-08,
      "loss": 0.0025,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.2754223942756653,
      "eval_runtime": 10.7209,
      "eval_samples_per_second": 349.784,
      "eval_steps_per_second": 5.503,
      "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
}