Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0430

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0430
File size: 3,668 Bytes 
595cf11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9552,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0430/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": 0.20055964589118958,
      "learning_rate": 6.733578363789503e-05,
      "loss": 0.6724,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9370666666666667,
      "eval_loss": 0.23268720507621765,
      "eval_runtime": 5.6549,
      "eval_samples_per_second": 663.145,
      "eval_steps_per_second": 10.433,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.9777905730703695e-05,
      "loss": 0.1217,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.19140231609344482,
      "eval_runtime": 5.622,
      "eval_samples_per_second": 667.018,
      "eval_steps_per_second": 10.494,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 4.8470148469326895e-05,
      "loss": 0.0546,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9477333333333333,
      "eval_loss": 0.195471853017807,
      "eval_runtime": 5.6132,
      "eval_samples_per_second": 668.073,
      "eval_steps_per_second": 10.511,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.20535875856876373,
      "learning_rate": 3.508254927997938e-05,
      "loss": 0.0231,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9485333333333333,
      "eval_loss": 0.19842477142810822,
      "eval_runtime": 5.6353,
      "eval_samples_per_second": 665.448,
      "eval_steps_per_second": 10.47,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.04457338526844978,
      "learning_rate": 2.1682382711066092e-05,
      "loss": 0.01,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9530666666666666,
      "eval_loss": 0.19286273419857025,
      "eval_runtime": 5.7299,
      "eval_samples_per_second": 654.458,
      "eval_steps_per_second": 10.297,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.02543989010155201,
      "learning_rate": 1.0309702649891636e-05,
      "loss": 0.0051,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9525333333333333,
      "eval_loss": 0.19932705163955688,
      "eval_runtime": 6.448,
      "eval_samples_per_second": 581.576,
      "eval_steps_per_second": 9.15,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.02309490367770195,
      "learning_rate": 2.6958965421683553e-06,
      "loss": 0.0026,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9552,
      "eval_loss": 0.1949717104434967,
      "eval_runtime": 5.6205,
      "eval_samples_per_second": 667.197,
      "eval_steps_per_second": 10.497,
      "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
}