Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0600

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0600
File size: 3,247 Bytes 
56464a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9386666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0600/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": 8.55698766265509e-05,
      "loss": 0.6793,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9125333333333333,
      "eval_loss": 0.3025802969932556,
      "eval_runtime": 12.0104,
      "eval_samples_per_second": 312.229,
      "eval_steps_per_second": 4.912,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1528008133172989,
      "learning_rate": 7.310443249967126e-05,
      "loss": 0.1557,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9144,
      "eval_loss": 0.2986544072628021,
      "eval_runtime": 11.9479,
      "eval_samples_per_second": 313.862,
      "eval_steps_per_second": 4.938,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7880029082298279,
      "learning_rate": 5.5072560837986624e-05,
      "loss": 0.0735,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9232,
      "eval_loss": 0.26791420578956604,
      "eval_runtime": 11.994,
      "eval_samples_per_second": 312.657,
      "eval_steps_per_second": 4.919,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.016575781628489494,
      "learning_rate": 3.504569497048685e-05,
      "loss": 0.0308,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9336,
      "eval_loss": 0.24338264763355255,
      "eval_runtime": 12.0736,
      "eval_samples_per_second": 310.596,
      "eval_steps_per_second": 4.887,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.18431459367275238,
      "learning_rate": 1.6990401295621727e-05,
      "loss": 0.0109,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.25956442952156067,
      "eval_runtime": 11.839,
      "eval_samples_per_second": 316.751,
      "eval_steps_per_second": 4.984,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.030175797641277313,
      "learning_rate": 4.48275215934364e-06,
      "loss": 0.0054,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.2519315183162689,
      "eval_runtime": 11.9644,
      "eval_samples_per_second": 313.43,
      "eval_steps_per_second": 4.931,
      "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
}