Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0603

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0603
File size: 3,647 Bytes 
e61c45a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.9618666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0603/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.17592252790927887,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5557,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9346666666666666,
      "eval_loss": 0.22985033690929413,
      "eval_runtime": 12.3892,
      "eval_samples_per_second": 302.682,
      "eval_steps_per_second": 4.762,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.029360411688685417,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.104,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.17673951387405396,
      "eval_runtime": 13.1951,
      "eval_samples_per_second": 284.197,
      "eval_steps_per_second": 4.471,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6451742649078369,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0419,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9461333333333334,
      "eval_loss": 0.19857564568519592,
      "eval_runtime": 12.2714,
      "eval_samples_per_second": 305.589,
      "eval_steps_per_second": 4.808,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.044737402349710464,
      "learning_rate": 5e-05,
      "loss": 0.0139,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.952,
      "eval_loss": 0.19062431156635284,
      "eval_runtime": 12.2969,
      "eval_samples_per_second": 304.955,
      "eval_steps_per_second": 4.798,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.005194774363189936,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0046,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.956,
      "eval_loss": 0.17767223715782166,
      "eval_runtime": 12.2005,
      "eval_samples_per_second": 307.365,
      "eval_steps_per_second": 4.836,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.011198839172720909,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0019,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9592,
      "eval_loss": 0.17283226549625397,
      "eval_runtime": 12.1907,
      "eval_samples_per_second": 307.612,
      "eval_steps_per_second": 4.84,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 3.82861996937452e-06,
      "loss": 0.001,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9618666666666666,
      "eval_loss": 0.1693526804447174,
      "eval_runtime": 12.0021,
      "eval_samples_per_second": 312.445,
      "eval_steps_per_second": 4.916,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}