Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0558

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0558
File size: 3,284 Bytes 
6253e07
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9490666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0558/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": 0.24629126489162445,
      "learning_rate": 7.714285714285714e-05,
      "loss": 0.6555,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9189333333333334,
      "eval_loss": 0.28301510214805603,
      "eval_runtime": 12.5537,
      "eval_samples_per_second": 298.718,
      "eval_steps_per_second": 4.7,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 37.91184616088867,
      "learning_rate": 6.428571428571429e-05,
      "loss": 0.1366,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9346666666666666,
      "eval_loss": 0.2330431342124939,
      "eval_runtime": 11.8289,
      "eval_samples_per_second": 317.02,
      "eval_steps_per_second": 4.988,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03248164802789688,
      "learning_rate": 5.142857142857143e-05,
      "loss": 0.0624,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9416,
      "eval_loss": 0.22513297200202942,
      "eval_runtime": 11.6887,
      "eval_samples_per_second": 320.821,
      "eval_steps_per_second": 5.048,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.039275024086236954,
      "learning_rate": 3.857142857142857e-05,
      "loss": 0.0253,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9408,
      "eval_loss": 0.24709554016590118,
      "eval_runtime": 11.5543,
      "eval_samples_per_second": 324.554,
      "eval_steps_per_second": 5.106,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.03094794787466526,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 0.0096,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9474666666666667,
      "eval_loss": 0.23058974742889404,
      "eval_runtime": 11.3244,
      "eval_samples_per_second": 331.145,
      "eval_steps_per_second": 5.21,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.038116369396448135,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 0.0039,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9490666666666666,
      "eval_loss": 0.2263736128807068,
      "eval_runtime": 11.0806,
      "eval_samples_per_second": 338.429,
      "eval_steps_per_second": 5.325,
      "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
}