Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0873

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0873
File size: 2,863 Bytes 
bb0b72c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9624,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0873/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": 3.578448534011841,
      "learning_rate": 6.733578363789503e-05,
      "loss": 0.6766,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9410666666666667,
      "eval_loss": 0.23265062272548676,
      "eval_runtime": 10.8908,
      "eval_samples_per_second": 344.327,
      "eval_steps_per_second": 5.417,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2248871773481369,
      "learning_rate": 5.974873734152915e-05,
      "loss": 0.0922,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.19261953234672546,
      "eval_runtime": 10.3048,
      "eval_samples_per_second": 363.907,
      "eval_steps_per_second": 5.725,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.02273142896592617,
      "learning_rate": 4.839392013277814e-05,
      "loss": 0.0351,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9578666666666666,
      "eval_loss": 0.17581170797348022,
      "eval_runtime": 10.7902,
      "eval_samples_per_second": 347.538,
      "eval_steps_per_second": 5.468,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05463125929236412,
      "learning_rate": 3.5e-05,
      "loss": 0.0087,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9605333333333334,
      "eval_loss": 0.1707434356212616,
      "eval_runtime": 10.2022,
      "eval_samples_per_second": 367.569,
      "eval_steps_per_second": 5.783,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.08693655580282211,
      "learning_rate": 2.1606079867221858e-05,
      "loss": 0.0031,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9624,
      "eval_loss": 0.17346756160259247,
      "eval_runtime": 10.2055,
      "eval_samples_per_second": 367.45,
      "eval_steps_per_second": 5.781,
      "step": 1665
    }
  ],
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}