Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0768

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0768
File size: 3,283 Bytes 
d0aa5d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9493333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0768/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": 8.400647327635769e-05,
      "loss": 0.6131,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9178666666666667,
      "eval_loss": 0.26617714762687683,
      "eval_runtime": 11.9544,
      "eval_samples_per_second": 313.692,
      "eval_steps_per_second": 4.935,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.60548973083496,
      "learning_rate": 6.756124916644227e-05,
      "loss": 0.1166,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9312,
      "eval_loss": 0.2359425127506256,
      "eval_runtime": 12.4792,
      "eval_samples_per_second": 300.5,
      "eval_steps_per_second": 4.728,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.1086097955703735,
      "learning_rate": 4.5070756562141305e-05,
      "loss": 0.039,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9402666666666667,
      "eval_loss": 0.22071491181850433,
      "eval_runtime": 11.8757,
      "eval_samples_per_second": 315.771,
      "eval_steps_per_second": 4.968,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12196424603462219,
      "learning_rate": 2.2561304794155375e-05,
      "loss": 0.0123,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9474666666666667,
      "eval_loss": 0.20547930896282196,
      "eval_runtime": 11.8625,
      "eval_samples_per_second": 316.123,
      "eval_steps_per_second": 4.974,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.013439030386507511,
      "learning_rate": 6.06428328578363e-06,
      "loss": 0.0034,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9490666666666666,
      "eval_loss": 0.21298886835575104,
      "eval_runtime": 12.124,
      "eval_samples_per_second": 309.303,
      "eval_steps_per_second": 4.866,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.025465982034802437,
      "learning_rate": 5.5627713115846694e-11,
      "loss": 0.0021,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9493333333333334,
      "eval_loss": 0.21239736676216125,
      "eval_runtime": 11.9602,
      "eval_samples_per_second": 313.54,
      "eval_steps_per_second": 4.933,
      "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
}