Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0923

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0923
File size: 3,270 Bytes 
42e985e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9474666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0923/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 8.659485808097889e-05,
      "loss": 0.643,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9224,
      "eval_loss": 0.2693433463573456,
      "eval_runtime": 5.9732,
      "eval_samples_per_second": 627.801,
      "eval_steps_per_second": 9.877,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1408175230026245,
      "learning_rate": 7.685730736804761e-05,
      "loss": 0.1383,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_loss": 0.23533761501312256,
      "eval_runtime": 5.9443,
      "eval_samples_per_second": 630.856,
      "eval_steps_per_second": 9.925,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.979540824890137,
      "learning_rate": 6.226977039554153e-05,
      "loss": 0.0758,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9370666666666667,
      "eval_loss": 0.23743252456188202,
      "eval_runtime": 5.8267,
      "eval_samples_per_second": 643.594,
      "eval_steps_per_second": 10.126,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04191936179995537,
      "learning_rate": 4.505306743117272e-05,
      "loss": 0.035,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9413333333333334,
      "eval_loss": 0.22180181741714478,
      "eval_runtime": 5.886,
      "eval_samples_per_second": 637.103,
      "eval_steps_per_second": 10.024,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0072874329052865505,
      "learning_rate": 2.7828285431465317e-05,
      "loss": 0.0146,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.23193655908107758,
      "eval_runtime": 6.2051,
      "eval_samples_per_second": 604.345,
      "eval_steps_per_second": 9.508,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.09468039125204086,
      "learning_rate": 1.3217741312837138e-05,
      "loss": 0.0054,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9474666666666667,
      "eval_loss": 0.21068871021270752,
      "eval_runtime": 5.8968,
      "eval_samples_per_second": 635.937,
      "eval_steps_per_second": 10.005,
      "step": 1998
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}