Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0556

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0556
File size: 3,227 Bytes 
aa24a5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_0556/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": 4.04857063293457,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 1.2565,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9088,
      "eval_loss": 0.35714074969291687,
      "eval_runtime": 11.9675,
      "eval_samples_per_second": 313.349,
      "eval_steps_per_second": 4.93,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.17686653137207,
      "learning_rate": 2.25e-05,
      "loss": 0.2256,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9253333333333333,
      "eval_loss": 0.2607901990413666,
      "eval_runtime": 11.146,
      "eval_samples_per_second": 336.445,
      "eval_steps_per_second": 5.293,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.757774353027344,
      "learning_rate": 1.5e-05,
      "loss": 0.117,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9344,
      "eval_loss": 0.23605360090732574,
      "eval_runtime": 10.9941,
      "eval_samples_per_second": 341.092,
      "eval_steps_per_second": 5.367,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05806867778301239,
      "learning_rate": 7.500000000000004e-06,
      "loss": 0.0656,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_loss": 0.2220790982246399,
      "eval_runtime": 11.1349,
      "eval_samples_per_second": 336.778,
      "eval_steps_per_second": 5.299,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3022714853286743,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 0.0395,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9330666666666667,
      "eval_loss": 0.23465374112129211,
      "eval_runtime": 11.2382,
      "eval_samples_per_second": 333.682,
      "eval_steps_per_second": 5.25,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.268687725067139,
      "learning_rate": 0.0,
      "loss": 0.03,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.21849378943443298,
      "eval_runtime": 11.5348,
      "eval_samples_per_second": 325.104,
      "eval_steps_per_second": 5.115,
      "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
}