Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0221

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0221
File size: 3,562 Bytes 
e359fb8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9309333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0221/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": 11.164518356323242,
      "learning_rate": 0.0001,
      "loss": 0.5934,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9264,
      "eval_loss": 0.25580430030822754,
      "eval_runtime": 5.6835,
      "eval_samples_per_second": 659.804,
      "eval_steps_per_second": 10.381,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.700750350952148,
      "learning_rate": 0.0001,
      "loss": 0.1548,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9253333333333333,
      "eval_loss": 0.25018489360809326,
      "eval_runtime": 5.594,
      "eval_samples_per_second": 670.359,
      "eval_steps_per_second": 10.547,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.12553507089614868,
      "learning_rate": 0.0001,
      "loss": 0.0982,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9205333333333333,
      "eval_loss": 0.2910597622394562,
      "eval_runtime": 5.686,
      "eval_samples_per_second": 659.515,
      "eval_steps_per_second": 10.376,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.018913432955741882,
      "learning_rate": 0.0001,
      "loss": 0.069,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9264,
      "eval_loss": 0.27449366450309753,
      "eval_runtime": 5.7138,
      "eval_samples_per_second": 656.311,
      "eval_steps_per_second": 10.326,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.021858008578419685,
      "learning_rate": 0.0001,
      "loss": 0.0574,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9218666666666666,
      "eval_loss": 0.3133319318294525,
      "eval_runtime": 6.0986,
      "eval_samples_per_second": 614.895,
      "eval_steps_per_second": 9.674,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01968323439359665,
      "learning_rate": 0.0001,
      "loss": 0.046,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.928,
      "eval_loss": 0.306606650352478,
      "eval_runtime": 5.8908,
      "eval_samples_per_second": 636.588,
      "eval_steps_per_second": 10.016,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 5.922869682312012,
      "learning_rate": 0.0001,
      "loss": 0.0403,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.3050827085971832,
      "eval_runtime": 6.1166,
      "eval_samples_per_second": 613.083,
      "eval_steps_per_second": 9.646,
      "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
}