Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0736

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0736
File size: 3,285 Bytes 
29dba2f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9162666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0736/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": 0.00028523292208850295,
      "loss": 0.659,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8384,
      "eval_loss": 0.52315753698349,
      "eval_runtime": 11.2878,
      "eval_samples_per_second": 332.217,
      "eval_steps_per_second": 5.227,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.10669116675853729,
      "learning_rate": 0.00024368144166557083,
      "loss": 0.3103,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.4733867943286896,
      "eval_runtime": 11.0857,
      "eval_samples_per_second": 338.274,
      "eval_steps_per_second": 5.322,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.208660125732422,
      "learning_rate": 0.0001835752027932887,
      "loss": 0.1889,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.43746495246887207,
      "eval_runtime": 11.983,
      "eval_samples_per_second": 312.943,
      "eval_steps_per_second": 4.924,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.40172502398490906,
      "learning_rate": 0.00011681898323495616,
      "loss": 0.0958,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8938666666666667,
      "eval_loss": 0.3945351243019104,
      "eval_runtime": 10.8878,
      "eval_samples_per_second": 344.422,
      "eval_steps_per_second": 5.419,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.14810645580291748,
      "learning_rate": 5.663467098540575e-05,
      "loss": 0.0352,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9061333333333333,
      "eval_loss": 0.3539629280567169,
      "eval_runtime": 11.1287,
      "eval_samples_per_second": 336.966,
      "eval_steps_per_second": 5.302,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.047006141394376755,
      "learning_rate": 1.4942507197812131e-05,
      "loss": 0.0111,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9162666666666667,
      "eval_loss": 0.32787030935287476,
      "eval_runtime": 11.2626,
      "eval_samples_per_second": 332.961,
      "eval_steps_per_second": 5.239,
      "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
}