Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0039

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0039
File size: 3,284 Bytes 
4afb687
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9642666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0039/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": 9.334052586261965e-05,
      "loss": 0.5592,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9354666666666667,
      "eval_loss": 0.2269430309534073,
      "eval_runtime": 12.2788,
      "eval_samples_per_second": 305.405,
      "eval_steps_per_second": 4.805,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.835662305355072,
      "learning_rate": 7.506805462938029e-05,
      "loss": 0.0911,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9437333333333333,
      "eval_loss": 0.21199120581150055,
      "eval_runtime": 12.537,
      "eval_samples_per_second": 299.115,
      "eval_steps_per_second": 4.706,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2192528247833252,
      "learning_rate": 5.007861840237923e-05,
      "loss": 0.035,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9536,
      "eval_loss": 0.17977383732795715,
      "eval_runtime": 12.4437,
      "eval_samples_per_second": 301.357,
      "eval_steps_per_second": 4.741,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.08175700902938843,
      "learning_rate": 2.506811643795042e-05,
      "loss": 0.0096,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9634666666666667,
      "eval_loss": 0.15746740996837616,
      "eval_runtime": 12.9476,
      "eval_samples_per_second": 289.629,
      "eval_steps_per_second": 4.557,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.008353305980563164,
      "learning_rate": 6.738092539759589e-06,
      "loss": 0.0038,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9629333333333333,
      "eval_loss": 0.15381653606891632,
      "eval_runtime": 12.2786,
      "eval_samples_per_second": 305.409,
      "eval_steps_per_second": 4.805,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.019039172679185867,
      "learning_rate": 6.180857012871855e-11,
      "loss": 0.0027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9642666666666667,
      "eval_loss": 0.15015354752540588,
      "eval_runtime": 13.5892,
      "eval_samples_per_second": 275.954,
      "eval_steps_per_second": 4.342,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}