Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0205

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0205
File size: 2,803 Bytes 
89fd09d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9450666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0205/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": 19.737625122070312,
      "learning_rate": 5.6e-05,
      "loss": 0.7316,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9189333333333334,
      "eval_loss": 0.2691802978515625,
      "eval_runtime": 7.0113,
      "eval_samples_per_second": 534.853,
      "eval_steps_per_second": 8.415,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2010050117969513,
      "learning_rate": 4.2e-05,
      "loss": 0.1377,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9346666666666666,
      "eval_loss": 0.2110331654548645,
      "eval_runtime": 7.0815,
      "eval_samples_per_second": 529.546,
      "eval_steps_per_second": 8.332,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.113795205950737,
      "learning_rate": 2.8e-05,
      "loss": 0.058,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9397333333333333,
      "eval_loss": 0.21645133197307587,
      "eval_runtime": 7.2368,
      "eval_samples_per_second": 518.183,
      "eval_steps_per_second": 8.153,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04026426002383232,
      "learning_rate": 1.4e-05,
      "loss": 0.0215,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.20488059520721436,
      "eval_runtime": 6.8917,
      "eval_samples_per_second": 544.132,
      "eval_steps_per_second": 8.561,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.049411121755838394,
      "learning_rate": 0.0,
      "loss": 0.01,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9450666666666667,
      "eval_loss": 0.2101563811302185,
      "eval_runtime": 6.9798,
      "eval_samples_per_second": 537.264,
      "eval_steps_per_second": 8.453,
      "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
}