Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0382

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0382
File size: 2,774 Bytes 
077ec45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9373333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0382/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 9.146783828735352,
      "learning_rate": 7e-05,
      "loss": 0.6976,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9274666666666667,
      "eval_loss": 0.25823354721069336,
      "eval_runtime": 7.1546,
      "eval_samples_per_second": 524.14,
      "eval_steps_per_second": 8.246,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.10701180249452591,
      "learning_rate": 7e-05,
      "loss": 0.1294,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9272,
      "eval_loss": 0.25435319542884827,
      "eval_runtime": 6.9528,
      "eval_samples_per_second": 539.348,
      "eval_steps_per_second": 8.486,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 7e-05,
      "loss": 0.0715,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.232840433716774,
      "eval_runtime": 6.856,
      "eval_samples_per_second": 546.965,
      "eval_steps_per_second": 8.606,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.873289585113525,
      "learning_rate": 7e-05,
      "loss": 0.0483,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9352,
      "eval_loss": 0.24474014341831207,
      "eval_runtime": 7.605,
      "eval_samples_per_second": 493.097,
      "eval_steps_per_second": 7.758,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.00732174189761281,
      "learning_rate": 7e-05,
      "loss": 0.0307,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9373333333333334,
      "eval_loss": 0.251916766166687,
      "eval_runtime": 7.0098,
      "eval_samples_per_second": 534.963,
      "eval_steps_per_second": 8.417,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}