Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0210

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0210
File size: 2,830 Bytes 
b5ade33
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9496,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0210/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.25008392333984375,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6091,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9224,
      "eval_loss": 0.2810952067375183,
      "eval_runtime": 9.5507,
      "eval_samples_per_second": 392.639,
      "eval_steps_per_second": 6.178,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2484281063079834,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1238,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.22906075417995453,
      "eval_runtime": 7.2606,
      "eval_samples_per_second": 516.488,
      "eval_steps_per_second": 8.126,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.08646693825721741,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0454,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.22269737720489502,
      "eval_runtime": 8.3683,
      "eval_samples_per_second": 448.121,
      "eval_steps_per_second": 7.05,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.14555208384990692,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0142,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9456,
      "eval_loss": 0.1985088288784027,
      "eval_runtime": 6.9912,
      "eval_samples_per_second": 536.39,
      "eval_steps_per_second": 8.439,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.026346253231167793,
      "learning_rate": 0.0,
      "loss": 0.0059,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.1905297487974167,
      "eval_runtime": 10.5688,
      "eval_samples_per_second": 354.818,
      "eval_steps_per_second": 5.582,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}