Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0230

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0230
File size: 3,272 Bytes 
3b1eaf4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9541333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0230/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": 2.045916795730591,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5601,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9261333333333334,
      "eval_loss": 0.2501373887062073,
      "eval_runtime": 6.0781,
      "eval_samples_per_second": 616.969,
      "eval_steps_per_second": 9.707,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2570958137512207,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1131,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9352,
      "eval_loss": 0.23773601651191711,
      "eval_runtime": 6.3452,
      "eval_samples_per_second": 590.999,
      "eval_steps_per_second": 9.298,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.027307456359267235,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0499,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9421333333333334,
      "eval_loss": 0.223721444606781,
      "eval_runtime": 6.6802,
      "eval_samples_per_second": 561.364,
      "eval_steps_per_second": 8.832,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.02087627723813057,
      "learning_rate": 5e-05,
      "loss": 0.0176,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9501333333333334,
      "eval_loss": 0.20575465261936188,
      "eval_runtime": 5.8663,
      "eval_samples_per_second": 639.242,
      "eval_steps_per_second": 10.057,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.00755307637155056,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0071,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9517333333333333,
      "eval_loss": 0.20079684257507324,
      "eval_runtime": 6.8526,
      "eval_samples_per_second": 547.234,
      "eval_steps_per_second": 8.61,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.008790192194283009,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0023,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9541333333333334,
      "eval_loss": 0.19679105281829834,
      "eval_runtime": 7.0396,
      "eval_samples_per_second": 532.7,
      "eval_steps_per_second": 8.381,
      "step": 1998
    }
  ],
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}