Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0867

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0867
File size: 3,976 Bytes 
6db84e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9178666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0867/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": 0.31312480568885803,
      "learning_rate": 0.0004375,
      "loss": 0.7971,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8037333333333333,
      "eval_loss": 0.7069745063781738,
      "eval_runtime": 13.5996,
      "eval_samples_per_second": 275.743,
      "eval_steps_per_second": 4.338,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3345870971679688,
      "learning_rate": 0.000375,
      "loss": 0.4282,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.5123467445373535,
      "eval_runtime": 13.4429,
      "eval_samples_per_second": 278.958,
      "eval_steps_per_second": 4.389,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.8722612857818604,
      "learning_rate": 0.0003125,
      "loss": 0.2679,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8552,
      "eval_loss": 0.5223559141159058,
      "eval_runtime": 13.3982,
      "eval_samples_per_second": 279.889,
      "eval_steps_per_second": 4.404,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.017099643126130104,
      "learning_rate": 0.00025,
      "loss": 0.1639,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8669333333333333,
      "eval_loss": 0.5227578282356262,
      "eval_runtime": 13.5298,
      "eval_samples_per_second": 277.165,
      "eval_steps_per_second": 4.361,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.017281346023082733,
      "learning_rate": 0.0001875,
      "loss": 0.0913,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8845333333333333,
      "eval_loss": 0.4356042444705963,
      "eval_runtime": 13.3572,
      "eval_samples_per_second": 280.748,
      "eval_steps_per_second": 4.417,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01304173655807972,
      "learning_rate": 0.000125,
      "loss": 0.0435,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8952,
      "eval_loss": 0.4435809850692749,
      "eval_runtime": 13.4464,
      "eval_samples_per_second": 278.886,
      "eval_steps_per_second": 4.388,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 6.26876876876877e-05,
      "loss": 0.0159,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9112,
      "eval_loss": 0.36990660429000854,
      "eval_runtime": 13.5021,
      "eval_samples_per_second": 277.734,
      "eval_steps_per_second": 4.37,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.00463523156940937,
      "learning_rate": 1.876876876876877e-07,
      "loss": 0.0038,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9178666666666667,
      "eval_loss": 0.35636457800865173,
      "eval_runtime": 13.6768,
      "eval_samples_per_second": 274.187,
      "eval_steps_per_second": 4.314,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}