Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0786

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0786
File size: 3,243 Bytes 
3a72b26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9456,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0786/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": 0.2746707797050476,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6088,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.928,
      "eval_loss": 0.23748891055583954,
      "eval_runtime": 5.3319,
      "eval_samples_per_second": 703.318,
      "eval_steps_per_second": 11.066,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.08713909983634949,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1194,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9290666666666667,
      "eval_loss": 0.24468694627285004,
      "eval_runtime": 5.394,
      "eval_samples_per_second": 695.216,
      "eval_steps_per_second": 10.938,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.032173290848731995,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0541,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9336,
      "eval_loss": 0.25124552845954895,
      "eval_runtime": 5.3687,
      "eval_samples_per_second": 698.492,
      "eval_steps_per_second": 10.99,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.018000254407525063,
      "learning_rate": 5e-05,
      "loss": 0.0174,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.23462770879268646,
      "eval_runtime": 5.3394,
      "eval_samples_per_second": 702.33,
      "eval_steps_per_second": 11.05,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.008777188137173653,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.005,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9418666666666666,
      "eval_loss": 0.24184514582157135,
      "eval_runtime": 5.3981,
      "eval_samples_per_second": 694.695,
      "eval_steps_per_second": 10.93,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.007952984422445297,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0018,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9456,
      "eval_loss": 0.2381117343902588,
      "eval_runtime": 5.3429,
      "eval_samples_per_second": 701.871,
      "eval_steps_per_second": 11.043,
      "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
}