Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0770

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0770
File size: 2,854 Bytes 
78dc5b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9461333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0770/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.133092999458313,
      "learning_rate": 2.5e-05,
      "loss": 1.2183,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.92,
      "eval_loss": 0.34095969796180725,
      "eval_runtime": 11.6948,
      "eval_samples_per_second": 320.655,
      "eval_steps_per_second": 5.045,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.745431900024414,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.1955,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9338666666666666,
      "eval_loss": 0.23937462270259857,
      "eval_runtime": 11.8425,
      "eval_samples_per_second": 316.656,
      "eval_steps_per_second": 4.982,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.125850200653076,
      "learning_rate": 1.5e-05,
      "loss": 0.09,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.2040974497795105,
      "eval_runtime": 11.7919,
      "eval_samples_per_second": 318.015,
      "eval_steps_per_second": 5.003,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12186428159475327,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.0451,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9429333333333333,
      "eval_loss": 0.20834214985370636,
      "eval_runtime": 11.9202,
      "eval_samples_per_second": 314.591,
      "eval_steps_per_second": 4.95,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.828379154205322,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.0231,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9461333333333334,
      "eval_loss": 0.20144446194171906,
      "eval_runtime": 11.8116,
      "eval_samples_per_second": 317.486,
      "eval_steps_per_second": 4.995,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}