Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0148

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0148
File size: 3,303 Bytes 
1ded442
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9501333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0148/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": 0.15119881927967072,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6062,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9178666666666667,
      "eval_loss": 0.26533761620521545,
      "eval_runtime": 7.4896,
      "eval_samples_per_second": 500.692,
      "eval_steps_per_second": 7.878,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 36.917518615722656,
      "learning_rate": 7.506805462938029e-05,
      "loss": 0.1232,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.21936246752738953,
      "eval_runtime": 5.9971,
      "eval_samples_per_second": 625.307,
      "eval_steps_per_second": 9.838,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03029683791100979,
      "learning_rate": 5.007861840237923e-05,
      "loss": 0.0485,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.2215277999639511,
      "eval_runtime": 6.2502,
      "eval_samples_per_second": 599.985,
      "eval_steps_per_second": 9.44,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.03810779005289078,
      "learning_rate": 2.506811643795042e-05,
      "loss": 0.0145,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9474666666666667,
      "eval_loss": 0.20606273412704468,
      "eval_runtime": 5.9584,
      "eval_samples_per_second": 629.364,
      "eval_steps_per_second": 9.902,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.11507808417081833,
      "learning_rate": 6.738092539759589e-06,
      "loss": 0.0046,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9493333333333334,
      "eval_loss": 0.19999708235263824,
      "eval_runtime": 6.0779,
      "eval_samples_per_second": 616.985,
      "eval_steps_per_second": 9.707,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.048500560224056244,
      "learning_rate": 6.180857012871855e-11,
      "loss": 0.0027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9501333333333334,
      "eval_loss": 0.19583867490291595,
      "eval_runtime": 6.8152,
      "eval_samples_per_second": 550.243,
      "eval_steps_per_second": 8.657,
      "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
}