Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0563

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0563
File size: 3,225 Bytes 
ef68674
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9154666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0563/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": 0.8101945519447327,
      "learning_rate": 0.00046650635094610973,
      "loss": 0.8149,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8328,
      "eval_loss": 0.5573840141296387,
      "eval_runtime": 10.1495,
      "eval_samples_per_second": 369.475,
      "eval_steps_per_second": 5.813,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.0166544914245605,
      "learning_rate": 0.000375,
      "loss": 0.3999,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8341333333333333,
      "eval_loss": 0.5705339908599854,
      "eval_runtime": 10.2106,
      "eval_samples_per_second": 367.266,
      "eval_steps_per_second": 5.778,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.29035359621047974,
      "learning_rate": 0.00025,
      "loss": 0.2086,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.4860474169254303,
      "eval_runtime": 10.7418,
      "eval_samples_per_second": 349.103,
      "eval_steps_per_second": 5.493,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.023704614490270615,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.0811,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8984,
      "eval_loss": 0.3932492136955261,
      "eval_runtime": 10.4523,
      "eval_samples_per_second": 358.771,
      "eval_steps_per_second": 5.645,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 12.4906644821167,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0137,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9144,
      "eval_loss": 0.35788312554359436,
      "eval_runtime": 10.1951,
      "eval_samples_per_second": 367.824,
      "eval_steps_per_second": 5.787,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.004096888937056065,
      "learning_rate": 0.0,
      "loss": 0.0021,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.3533007800579071,
      "eval_runtime": 10.7104,
      "eval_samples_per_second": 350.127,
      "eval_steps_per_second": 5.509,
      "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
}