Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0202

Safetensors
vit
Model card Files
xet
Community
Model-J__SupViT__model_idx_0202
File size: 2,438 Bytes 
3d2465d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9522666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0202/checkpoints/checkpoint-1332",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1332,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.049002647399902,
      "learning_rate": 8.397114317029975e-05,
      "loss": 0.6414,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9274666666666667,
      "eval_loss": 0.26497218012809753,
      "eval_runtime": 6.5932,
      "eval_samples_per_second": 568.77,
      "eval_steps_per_second": 8.949,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6770778298377991,
      "learning_rate": 6.75e-05,
      "loss": 0.1119,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.2325042337179184,
      "eval_runtime": 6.4419,
      "eval_samples_per_second": 582.128,
      "eval_steps_per_second": 9.159,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04513607546687126,
      "learning_rate": 4.5e-05,
      "loss": 0.0373,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9432,
      "eval_loss": 0.2246512919664383,
      "eval_runtime": 6.2082,
      "eval_samples_per_second": 604.043,
      "eval_steps_per_second": 9.504,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.02674630656838417,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.0096,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9522666666666667,
      "eval_loss": 0.19853371381759644,
      "eval_runtime": 6.169,
      "eval_samples_per_second": 607.877,
      "eval_steps_per_second": 9.564,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 6.58965282490368e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}