Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0175

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0175
File size: 3,146 Bytes 
6854142
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8352,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0175/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": 1.3336267471313477,
      "learning_rate": 0.0005,
      "loss": 0.7951,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8136,
      "eval_loss": 0.6148720979690552,
      "eval_runtime": 8.2084,
      "eval_samples_per_second": 456.849,
      "eval_steps_per_second": 7.188,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5166281461715698,
      "learning_rate": 0.0005,
      "loss": 0.5089,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8138666666666666,
      "eval_loss": 0.6237390637397766,
      "eval_runtime": 7.4665,
      "eval_samples_per_second": 502.244,
      "eval_steps_per_second": 7.902,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.9566516876220703,
      "learning_rate": 0.0005,
      "loss": 0.3948,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8168,
      "eval_loss": 0.6680936813354492,
      "eval_runtime": 7.7951,
      "eval_samples_per_second": 481.074,
      "eval_steps_per_second": 7.569,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07566697150468826,
      "learning_rate": 0.0005,
      "loss": 0.3368,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8106666666666666,
      "eval_loss": 0.6573176980018616,
      "eval_runtime": 8.0476,
      "eval_samples_per_second": 465.975,
      "eval_steps_per_second": 7.331,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.050144851207733154,
      "learning_rate": 0.0005,
      "loss": 0.2812,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8064,
      "eval_loss": 0.6659818887710571,
      "eval_runtime": 7.6696,
      "eval_samples_per_second": 488.945,
      "eval_steps_per_second": 7.693,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6744274497032166,
      "learning_rate": 0.0005,
      "loss": 0.2555,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.600970983505249,
      "eval_runtime": 7.6273,
      "eval_samples_per_second": 491.654,
      "eval_steps_per_second": 7.735,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}