Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0190

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0190
File size: 3,229 Bytes 
df91b94
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9208,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0190/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": 14.247560501098633,
      "learning_rate": 0.0004166666666666667,
      "loss": 0.7775,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8312,
      "eval_loss": 0.5685111880302429,
      "eval_runtime": 7.1826,
      "eval_samples_per_second": 522.094,
      "eval_steps_per_second": 8.214,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.03333624452352524,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.3984,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.5177866816520691,
      "eval_runtime": 7.2894,
      "eval_samples_per_second": 514.443,
      "eval_steps_per_second": 8.094,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 11.747617721557617,
      "learning_rate": 0.00025,
      "loss": 0.227,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.4732254445552826,
      "eval_runtime": 7.3924,
      "eval_samples_per_second": 507.278,
      "eval_steps_per_second": 7.981,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.4018425941467285,
      "learning_rate": 0.00016666666666666666,
      "loss": 0.1202,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8861333333333333,
      "eval_loss": 0.42865604162216187,
      "eval_runtime": 6.863,
      "eval_samples_per_second": 546.412,
      "eval_steps_per_second": 8.597,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.011962993070483208,
      "learning_rate": 8.333333333333333e-05,
      "loss": 0.0469,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9138666666666667,
      "eval_loss": 0.3460049331188202,
      "eval_runtime": 6.9287,
      "eval_samples_per_second": 541.227,
      "eval_steps_per_second": 8.515,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.10341998189687729,
      "learning_rate": 0.0,
      "loss": 0.0092,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9208,
      "eval_loss": 0.3344506323337555,
      "eval_runtime": 7.1144,
      "eval_samples_per_second": 527.098,
      "eval_steps_per_second": 8.293,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}