Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0426

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0426
File size: 3,291 Bytes 
c8b785c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9210666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0426/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": 0.00046670262931309826,
      "loss": 0.7522,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.5973968505859375,
      "eval_runtime": 11.363,
      "eval_samples_per_second": 330.018,
      "eval_steps_per_second": 5.192,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.946948051452637,
      "learning_rate": 0.00037534027314690147,
      "loss": 0.3782,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8605333333333334,
      "eval_loss": 0.4985889792442322,
      "eval_runtime": 11.2934,
      "eval_samples_per_second": 332.054,
      "eval_steps_per_second": 5.224,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.19015716016292572,
      "learning_rate": 0.00025039309201189616,
      "loss": 0.1948,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8685333333333334,
      "eval_loss": 0.4911174476146698,
      "eval_runtime": 11.1621,
      "eval_samples_per_second": 335.958,
      "eval_steps_per_second": 5.286,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.157136917114258,
      "learning_rate": 0.00012534058218975207,
      "loss": 0.0705,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.38324952125549316,
      "eval_runtime": 10.8468,
      "eval_samples_per_second": 345.723,
      "eval_steps_per_second": 5.439,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0249284505844116,
      "learning_rate": 3.369046269879794e-05,
      "loss": 0.012,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9157333333333333,
      "eval_loss": 0.323090136051178,
      "eval_runtime": 10.439,
      "eval_samples_per_second": 359.23,
      "eval_steps_per_second": 5.652,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.007587837055325508,
      "learning_rate": 3.090428506435927e-10,
      "loss": 0.0023,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9210666666666667,
      "eval_loss": 0.32039955258369446,
      "eval_runtime": 10.4122,
      "eval_samples_per_second": 360.156,
      "eval_steps_per_second": 5.666,
      "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
}