Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0650

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0650
File size: 4,504 Bytes 
60650db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9554666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0650/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": 0.46573513746261597,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.8817,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9341333333333334,
      "eval_loss": 0.2542448043823242,
      "eval_runtime": 16.1278,
      "eval_samples_per_second": 232.518,
      "eval_steps_per_second": 3.658,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 4.416794553834106e-05,
      "loss": 0.1474,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.2166237235069275,
      "eval_runtime": 12.9852,
      "eval_samples_per_second": 288.79,
      "eval_steps_per_second": 4.544,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.826171398162842,
      "learning_rate": 3.7522688315464166e-05,
      "loss": 0.0696,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9509333333333333,
      "eval_loss": 0.19319765269756317,
      "eval_runtime": 12.8981,
      "eval_samples_per_second": 290.741,
      "eval_steps_per_second": 4.574,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.03971899673342705,
      "learning_rate": 2.936701006654613e-05,
      "loss": 0.0306,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9482666666666667,
      "eval_loss": 0.20276851952075958,
      "eval_runtime": 13.1049,
      "eval_samples_per_second": 286.152,
      "eval_steps_per_second": 4.502,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.016659967601299286,
      "learning_rate": 2.0684605953398183e-05,
      "loss": 0.0148,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9485333333333333,
      "eval_loss": 0.19442978501319885,
      "eval_runtime": 12.9652,
      "eval_samples_per_second": 289.235,
      "eval_steps_per_second": 4.551,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.18600670993328094,
      "learning_rate": 1.2522702050703538e-05,
      "loss": 0.0077,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9517333333333333,
      "eval_loss": 0.19406355917453766,
      "eval_runtime": 12.678,
      "eval_samples_per_second": 295.789,
      "eval_steps_per_second": 4.654,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.02953970804810524,
      "learning_rate": 5.865744425999756e-06,
      "loss": 0.0038,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.19045233726501465,
      "eval_runtime": 13.1174,
      "eval_samples_per_second": 285.879,
      "eval_steps_per_second": 4.498,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.03360190987586975,
      "learning_rate": 1.5166604150571306e-06,
      "loss": 0.0028,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.952,
      "eval_loss": 0.1916361153125763,
      "eval_runtime": 13.033,
      "eval_samples_per_second": 287.732,
      "eval_steps_per_second": 4.527,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.05573350936174393,
      "learning_rate": 1.3735239379197851e-11,
      "loss": 0.0028,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9554666666666667,
      "eval_loss": 0.18405339121818542,
      "eval_runtime": 13.1083,
      "eval_samples_per_second": 286.078,
      "eval_steps_per_second": 4.501,
      "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
}