Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0696

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0696
File size: 4,479 Bytes 
a466dec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9077333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0696/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": 2.3898162841796875,
      "learning_rate": 0.0004849231551964771,
      "loss": 0.7769,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8245333333333333,
      "eval_loss": 0.5733988285064697,
      "eval_runtime": 7.3344,
      "eval_samples_per_second": 511.289,
      "eval_steps_per_second": 8.044,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.53957462310791,
      "learning_rate": 0.0004415111107797445,
      "loss": 0.4243,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8314666666666667,
      "eval_loss": 0.5607510209083557,
      "eval_runtime": 6.7244,
      "eval_samples_per_second": 557.674,
      "eval_steps_per_second": 8.774,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.331352174282074,
      "learning_rate": 0.000375,
      "loss": 0.2746,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8453333333333334,
      "eval_loss": 0.5231761336326599,
      "eval_runtime": 6.8992,
      "eval_samples_per_second": 543.539,
      "eval_steps_per_second": 8.552,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.19693371653556824,
      "learning_rate": 0.00029341204441673266,
      "loss": 0.1729,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8714666666666666,
      "eval_loss": 0.4695960283279419,
      "eval_runtime": 6.897,
      "eval_samples_per_second": 543.718,
      "eval_steps_per_second": 8.554,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00020684605953398183,
      "loss": 0.0922,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.4729515612125397,
      "eval_runtime": 6.7977,
      "eval_samples_per_second": 551.661,
      "eval_steps_per_second": 8.679,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.005368772428482771,
      "learning_rate": 0.00012522702050703539,
      "loss": 0.0313,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9034666666666666,
      "eval_loss": 0.42343100905418396,
      "eval_runtime": 6.9072,
      "eval_samples_per_second": 542.913,
      "eval_steps_per_second": 8.542,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0034648042637854815,
      "learning_rate": 5.8657444259997555e-05,
      "loss": 0.0058,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9061333333333333,
      "eval_loss": 0.3838595151901245,
      "eval_runtime": 6.6147,
      "eval_samples_per_second": 566.919,
      "eval_steps_per_second": 8.92,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.005470506846904755,
      "learning_rate": 1.5166604150571307e-05,
      "loss": 0.0018,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9072,
      "eval_loss": 0.38647598028182983,
      "eval_runtime": 7.736,
      "eval_samples_per_second": 484.745,
      "eval_steps_per_second": 7.627,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.022030405700206757,
      "learning_rate": 1.373523937919785e-10,
      "loss": 0.0012,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9077333333333333,
      "eval_loss": 0.385495126247406,
      "eval_runtime": 6.6942,
      "eval_samples_per_second": 560.185,
      "eval_steps_per_second": 8.814,
      "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
}