Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0141

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0141
File size: 4,457 Bytes 
6662ed3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.9429333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0141/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "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": 6.224557891224557e-05,
      "loss": 0.7492,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9144,
      "eval_loss": 0.2823871076107025,
      "eval_runtime": 6.9598,
      "eval_samples_per_second": 538.809,
      "eval_steps_per_second": 8.477,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.986521303653717,
      "learning_rate": 5.44678011344678e-05,
      "loss": 0.1534,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9304,
      "eval_loss": 0.22050654888153076,
      "eval_runtime": 7.0341,
      "eval_samples_per_second": 533.116,
      "eval_steps_per_second": 8.388,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.030354507267475128,
      "learning_rate": 4.669002335669002e-05,
      "loss": 0.0766,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.23294183611869812,
      "eval_runtime": 8.3941,
      "eval_samples_per_second": 446.744,
      "eval_steps_per_second": 7.029,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.023356100544333458,
      "learning_rate": 3.891224557891224e-05,
      "loss": 0.042,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.25827333331108093,
      "eval_runtime": 7.3007,
      "eval_samples_per_second": 513.653,
      "eval_steps_per_second": 8.081,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.011836192570626736,
      "learning_rate": 3.113446780113447e-05,
      "loss": 0.023,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9408,
      "eval_loss": 0.24119557440280914,
      "eval_runtime": 6.8228,
      "eval_samples_per_second": 549.628,
      "eval_steps_per_second": 8.647,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.05051024258136749,
      "learning_rate": 2.3356690023356685e-05,
      "loss": 0.0117,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.23503275215625763,
      "eval_runtime": 6.4054,
      "eval_samples_per_second": 585.442,
      "eval_steps_per_second": 9.211,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.10547558963298798,
      "learning_rate": 1.557891224557891e-05,
      "loss": 0.007,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9418666666666666,
      "eval_loss": 0.24215810000896454,
      "eval_runtime": 6.3762,
      "eval_samples_per_second": 588.123,
      "eval_steps_per_second": 9.253,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.017067061737179756,
      "learning_rate": 7.801134467801133e-06,
      "loss": 0.0031,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9418666666666666,
      "eval_loss": 0.2415737509727478,
      "eval_runtime": 6.3581,
      "eval_samples_per_second": 589.799,
      "eval_steps_per_second": 9.28,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.011283006519079208,
      "learning_rate": 2.3356690023356688e-08,
      "loss": 0.0021,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9429333333333333,
      "eval_loss": 0.229874849319458,
      "eval_runtime": 6.4503,
      "eval_samples_per_second": 581.364,
      "eval_steps_per_second": 9.147,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}