Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0725

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0725
File size: 3,273 Bytes 
9471443
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9386666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0725/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": 0.6151783466339111,
      "learning_rate": 0.0002501501501501501,
      "loss": 0.5944,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8722666666666666,
      "eval_loss": 0.43284857273101807,
      "eval_runtime": 13.1447,
      "eval_samples_per_second": 285.286,
      "eval_steps_per_second": 4.489,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.09106773138046265,
      "learning_rate": 0.00020015015015015014,
      "loss": 0.231,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8912,
      "eval_loss": 0.3900403678417206,
      "eval_runtime": 12.3906,
      "eval_samples_per_second": 302.648,
      "eval_steps_per_second": 4.762,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.020750045776367,
      "learning_rate": 0.00015015015015015014,
      "loss": 0.1149,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9112,
      "eval_loss": 0.320642352104187,
      "eval_runtime": 11.7733,
      "eval_samples_per_second": 318.517,
      "eval_steps_per_second": 5.011,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.11629350483417511,
      "learning_rate": 0.00010015015015015015,
      "loss": 0.0504,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9282666666666667,
      "eval_loss": 0.2796340584754944,
      "eval_runtime": 12.0596,
      "eval_samples_per_second": 310.957,
      "eval_steps_per_second": 4.892,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.008157548494637012,
      "learning_rate": 5.0150150150150145e-05,
      "loss": 0.0131,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9336,
      "eval_loss": 0.2753343880176544,
      "eval_runtime": 12.1814,
      "eval_samples_per_second": 307.845,
      "eval_steps_per_second": 4.843,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.019881099462509155,
      "learning_rate": 1.5015015015015014e-07,
      "loss": 0.0034,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.25723469257354736,
      "eval_runtime": 12.5701,
      "eval_samples_per_second": 298.328,
      "eval_steps_per_second": 4.694,
      "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
}