Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0457

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0457
File size: 3,296 Bytes 
4bd1b37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9173333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0457/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": 0.07800160348415375,
      "learning_rate": 0.00047524221697560476,
      "loss": 0.736,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7826666666666666,
      "eval_loss": 0.7545227408409119,
      "eval_runtime": 5.846,
      "eval_samples_per_second": 641.47,
      "eval_steps_per_second": 10.092,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.18772074580192566,
      "learning_rate": 0.0004058724504646834,
      "loss": 0.3908,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8445333333333334,
      "eval_loss": 0.5308092832565308,
      "eval_runtime": 5.7654,
      "eval_samples_per_second": 650.43,
      "eval_steps_per_second": 10.233,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.10216109454631805,
      "learning_rate": 0.0003056302334890786,
      "loss": 0.2277,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8658666666666667,
      "eval_loss": 0.46406376361846924,
      "eval_runtime": 5.8544,
      "eval_samples_per_second": 640.54,
      "eval_steps_per_second": 10.078,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.016328074038028717,
      "learning_rate": 0.00019436976651092142,
      "loss": 0.1159,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8850666666666667,
      "eval_loss": 0.43373844027519226,
      "eval_runtime": 5.8699,
      "eval_samples_per_second": 638.853,
      "eval_steps_per_second": 10.051,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.005870298016816378,
      "learning_rate": 9.412754953531663e-05,
      "loss": 0.0403,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9112,
      "eval_loss": 0.34586405754089355,
      "eval_runtime": 5.8332,
      "eval_samples_per_second": 642.87,
      "eval_steps_per_second": 10.114,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.005968926008790731,
      "learning_rate": 2.4757783024395242e-05,
      "loss": 0.0061,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9173333333333333,
      "eval_loss": 0.3278957009315491,
      "eval_runtime": 5.9325,
      "eval_samples_per_second": 632.112,
      "eval_steps_per_second": 9.945,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}