Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0705

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0705
File size: 3,665 Bytes 
13d4fd2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9450666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0705/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": 0.1518072634935379,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.6136,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9186666666666666,
      "eval_loss": 0.28624647855758667,
      "eval_runtime": 6.6565,
      "eval_samples_per_second": 563.361,
      "eval_steps_per_second": 8.864,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1595793217420578,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.1386,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9304,
      "eval_loss": 0.23829610645771027,
      "eval_runtime": 6.2838,
      "eval_samples_per_second": 596.775,
      "eval_steps_per_second": 9.389,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 5.718575718575719e-05,
      "loss": 0.0662,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.23129023611545563,
      "eval_runtime": 7.1005,
      "eval_samples_per_second": 528.133,
      "eval_steps_per_second": 8.309,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.030470101162791252,
      "learning_rate": 4.2900042900042906e-05,
      "loss": 0.0258,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9381333333333334,
      "eval_loss": 0.23101848363876343,
      "eval_runtime": 6.6641,
      "eval_samples_per_second": 562.72,
      "eval_steps_per_second": 8.853,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.01272925827652216,
      "learning_rate": 2.8614328614328617e-05,
      "loss": 0.0107,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9432,
      "eval_loss": 0.22972893714904785,
      "eval_runtime": 6.9679,
      "eval_samples_per_second": 538.186,
      "eval_steps_per_second": 8.467,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.05794566497206688,
      "learning_rate": 1.4328614328614328e-05,
      "loss": 0.0045,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.944,
      "eval_loss": 0.22752240300178528,
      "eval_runtime": 6.7036,
      "eval_samples_per_second": 559.404,
      "eval_steps_per_second": 8.801,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.006396161392331123,
      "learning_rate": 4.2900042900042903e-08,
      "loss": 0.003,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9450666666666667,
      "eval_loss": 0.22217436134815216,
      "eval_runtime": 6.5897,
      "eval_samples_per_second": 569.072,
      "eval_steps_per_second": 8.953,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}