Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0695

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0695
File size: 3,275 Bytes 
e72df56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9450666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0695/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": 2.572715572715573e-05,
      "loss": 1.2896,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9202666666666667,
      "eval_loss": 0.33153626322746277,
      "eval_runtime": 13.2251,
      "eval_samples_per_second": 283.551,
      "eval_steps_per_second": 4.461,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6616044640541077,
      "learning_rate": 2.1441441441441442e-05,
      "loss": 0.2015,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9354666666666667,
      "eval_loss": 0.23952467739582062,
      "eval_runtime": 12.9953,
      "eval_samples_per_second": 288.565,
      "eval_steps_per_second": 4.54,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7062535285949707,
      "learning_rate": 1.715572715572716e-05,
      "loss": 0.0921,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9429333333333333,
      "eval_loss": 0.22421015799045563,
      "eval_runtime": 13.1614,
      "eval_samples_per_second": 284.925,
      "eval_steps_per_second": 4.483,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04185378924012184,
      "learning_rate": 1.287001287001287e-05,
      "loss": 0.0439,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9416,
      "eval_loss": 0.22845660150051117,
      "eval_runtime": 13.0679,
      "eval_samples_per_second": 286.962,
      "eval_steps_per_second": 4.515,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.32101234793663025,
      "learning_rate": 8.584298584298585e-06,
      "loss": 0.023,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9408,
      "eval_loss": 0.22803154587745667,
      "eval_runtime": 13.1378,
      "eval_samples_per_second": 285.437,
      "eval_steps_per_second": 4.491,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.044718898832798004,
      "learning_rate": 4.298584298584299e-06,
      "loss": 0.0148,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9450666666666667,
      "eval_loss": 0.22224505245685577,
      "eval_runtime": 13.1456,
      "eval_samples_per_second": 285.266,
      "eval_steps_per_second": 4.488,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}