Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0325

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0325
File size: 2,878 Bytes 
9b387dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9549333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0325/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": Infinity,
      "learning_rate": 5.604204204204204e-05,
      "loss": 0.6601,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9410666666666667,
      "eval_loss": 0.20202353596687317,
      "eval_runtime": 6.5208,
      "eval_samples_per_second": 575.082,
      "eval_steps_per_second": 9.048,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7329742908477783,
      "learning_rate": 4.2042042042042036e-05,
      "loss": 0.096,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.19668349623680115,
      "eval_runtime": 6.4912,
      "eval_samples_per_second": 577.701,
      "eval_steps_per_second": 9.089,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.035918138921260834,
      "learning_rate": 2.8042042042042038e-05,
      "loss": 0.0321,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9517333333333333,
      "eval_loss": 0.17559915781021118,
      "eval_runtime": 6.5671,
      "eval_samples_per_second": 571.025,
      "eval_steps_per_second": 8.984,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.15722709894180298,
      "learning_rate": 1.404204204204204e-05,
      "loss": 0.0114,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9544,
      "eval_loss": 0.16773828864097595,
      "eval_runtime": 6.5391,
      "eval_samples_per_second": 573.473,
      "eval_steps_per_second": 9.023,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.033580388873815536,
      "learning_rate": 4.204204204204204e-08,
      "loss": 0.0049,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9549333333333333,
      "eval_loss": 0.17033600807189941,
      "eval_runtime": 6.5084,
      "eval_samples_per_second": 576.181,
      "eval_steps_per_second": 9.065,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}