Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0500

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0500
File size: 3,649 Bytes 
8eaea3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.9301333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0500/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00028523292208850295,
      "loss": 0.7022,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.4970744550228119,
      "eval_runtime": 8.1979,
      "eval_samples_per_second": 457.433,
      "eval_steps_per_second": 7.197,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.403156757354736,
      "learning_rate": 0.00024368144166557083,
      "loss": 0.3107,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.3966827988624573,
      "eval_runtime": 6.6524,
      "eval_samples_per_second": 563.706,
      "eval_steps_per_second": 8.869,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.33368104696273804,
      "learning_rate": 0.0001835752027932887,
      "loss": 0.1735,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.4058074355125427,
      "eval_runtime": 6.7899,
      "eval_samples_per_second": 552.292,
      "eval_steps_per_second": 8.689,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.03471895679831505,
      "learning_rate": 0.00011681898323495616,
      "loss": 0.0896,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9072,
      "eval_loss": 0.32155951857566833,
      "eval_runtime": 7.334,
      "eval_samples_per_second": 511.32,
      "eval_steps_per_second": 8.045,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.011566203087568283,
      "learning_rate": 5.663467098540575e-05,
      "loss": 0.0327,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9232,
      "eval_loss": 0.29135099053382874,
      "eval_runtime": 6.6828,
      "eval_samples_per_second": 561.141,
      "eval_steps_per_second": 8.829,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.16574816405773163,
      "learning_rate": 1.4942507197812131e-05,
      "loss": 0.0104,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9293333333333333,
      "eval_loss": 0.2756038010120392,
      "eval_runtime": 6.6317,
      "eval_samples_per_second": 565.463,
      "eval_steps_per_second": 8.897,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.008136553689837456,
      "learning_rate": 1.3623114161753767e-10,
      "loss": 0.0048,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9301333333333334,
      "eval_loss": 0.2775745093822479,
      "eval_runtime": 7.0003,
      "eval_samples_per_second": 535.694,
      "eval_steps_per_second": 8.428,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}