Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0496

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0496
File size: 3,234 Bytes 
1cfa59e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9264,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0496/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": 0.6189892292022705,
      "learning_rate": 0.0002851453301853628,
      "loss": 0.6446,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8464,
      "eval_loss": 0.5147414803504944,
      "eval_runtime": 13.374,
      "eval_samples_per_second": 280.395,
      "eval_steps_per_second": 4.412,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00024368144166557083,
      "loss": 0.3125,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.4222654402256012,
      "eval_runtime": 15.4946,
      "eval_samples_per_second": 242.02,
      "eval_steps_per_second": 3.808,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.02921995148062706,
      "learning_rate": 0.0001835752027932887,
      "loss": 0.1852,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.4717291295528412,
      "eval_runtime": 13.9524,
      "eval_samples_per_second": 268.77,
      "eval_steps_per_second": 4.229,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04617946594953537,
      "learning_rate": 0.00011681898323495616,
      "loss": 0.0988,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9016,
      "eval_loss": 0.36849215626716614,
      "eval_runtime": 13.9926,
      "eval_samples_per_second": 267.998,
      "eval_steps_per_second": 4.217,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.017399344593286514,
      "learning_rate": 5.663467098540575e-05,
      "loss": 0.0403,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9248,
      "eval_loss": 0.3074793517589569,
      "eval_runtime": 13.5894,
      "eval_samples_per_second": 275.951,
      "eval_steps_per_second": 4.342,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1372547149658203,
      "learning_rate": 1.4942507197812131e-05,
      "loss": 0.0119,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9264,
      "eval_loss": 0.3063312768936157,
      "eval_runtime": 16.5402,
      "eval_samples_per_second": 226.72,
      "eval_steps_per_second": 3.567,
      "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
}