Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0317

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0317
File size: 2,845 Bytes 
d37c464
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9368,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0317/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": 10.12156867980957,
      "learning_rate": 8.140576474687264e-05,
      "loss": 0.7062,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9058666666666667,
      "eval_loss": 0.3037542998790741,
      "eval_runtime": 6.9958,
      "eval_samples_per_second": 536.035,
      "eval_steps_per_second": 8.434,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3510514497756958,
      "learning_rate": 5.890576474687264e-05,
      "loss": 0.1656,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.30868396162986755,
      "eval_runtime": 6.4709,
      "eval_samples_per_second": 579.52,
      "eval_steps_per_second": 9.118,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3.117501217934705e-05,
      "loss": 0.0744,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9296,
      "eval_loss": 0.25816580653190613,
      "eval_runtime": 6.1576,
      "eval_samples_per_second": 609.008,
      "eval_steps_per_second": 9.582,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.035642754286527634,
      "learning_rate": 8.644207645970472e-06,
      "loss": 0.0258,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9357333333333333,
      "eval_loss": 0.24776002764701843,
      "eval_runtime": 6.7482,
      "eval_samples_per_second": 555.706,
      "eval_steps_per_second": 8.743,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2558751404285431,
      "learning_rate": 8.010389962842535e-11,
      "loss": 0.0124,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.23614606261253357,
      "eval_runtime": 6.283,
      "eval_samples_per_second": 596.845,
      "eval_steps_per_second": 9.39,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}