Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0940

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0940
File size: 4,030 Bytes 
6394d42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.9472,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0940/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 9.263103485107422,
      "learning_rate": 8.728616793536588e-05,
      "loss": 0.6214,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9232,
      "eval_loss": 0.26292070746421814,
      "eval_runtime": 10.9886,
      "eval_samples_per_second": 341.261,
      "eval_steps_per_second": 5.369,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.02275894209742546,
      "learning_rate": 7.947199994035401e-05,
      "loss": 0.1216,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9296,
      "eval_loss": 0.2450132817029953,
      "eval_runtime": 10.8191,
      "eval_samples_per_second": 346.609,
      "eval_steps_per_second": 5.453,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7359638810157776,
      "learning_rate": 6.75e-05,
      "loss": 0.0501,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9352,
      "eval_loss": 0.24296283721923828,
      "eval_runtime": 10.7918,
      "eval_samples_per_second": 347.485,
      "eval_steps_per_second": 5.467,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.09863725304603577,
      "learning_rate": 5.2814167995011876e-05,
      "loss": 0.0191,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9421333333333334,
      "eval_loss": 0.23649375140666962,
      "eval_runtime": 10.8653,
      "eval_samples_per_second": 345.135,
      "eval_steps_per_second": 5.43,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.06402511894702911,
      "learning_rate": 3.7185832004988136e-05,
      "loss": 0.0065,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9421333333333334,
      "eval_loss": 0.25039568543434143,
      "eval_runtime": 10.8287,
      "eval_samples_per_second": 346.303,
      "eval_steps_per_second": 5.449,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01055889017879963,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.0023,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9442666666666667,
      "eval_loss": 0.2443544864654541,
      "eval_runtime": 12.2264,
      "eval_samples_per_second": 306.712,
      "eval_steps_per_second": 4.826,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.055833996679956e-05,
      "loss": 0.001,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.24011436104774475,
      "eval_runtime": 10.8299,
      "eval_samples_per_second": 346.264,
      "eval_steps_per_second": 5.448,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.1084698885679245,
      "learning_rate": 2.7299887471028354e-06,
      "loss": 0.0008,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9472,
      "eval_loss": 0.2405838817358017,
      "eval_runtime": 10.7764,
      "eval_samples_per_second": 347.983,
      "eval_steps_per_second": 5.475,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}