Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0400

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0400
File size: 4,053 Bytes 
4b9558c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9469333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0400/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": 6.648773670196533,
      "learning_rate": 2.9095389311788626e-05,
      "loss": 1.1481,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.30702728033065796,
      "eval_runtime": 7.1758,
      "eval_samples_per_second": 522.591,
      "eval_steps_per_second": 8.222,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.16096726059913635,
      "learning_rate": 2.649066664678467e-05,
      "loss": 0.1716,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.24681493639945984,
      "eval_runtime": 7.1513,
      "eval_samples_per_second": 524.377,
      "eval_steps_per_second": 8.25,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.7270374298095703,
      "learning_rate": 2.25e-05,
      "loss": 0.0794,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9389333333333333,
      "eval_loss": 0.21328647434711456,
      "eval_runtime": 7.0626,
      "eval_samples_per_second": 530.967,
      "eval_steps_per_second": 8.354,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.1219775602221489,
      "learning_rate": 1.760472266500396e-05,
      "loss": 0.039,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9402666666666667,
      "eval_loss": 0.22654584050178528,
      "eval_runtime": 6.9307,
      "eval_samples_per_second": 541.069,
      "eval_steps_per_second": 8.513,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.04188675060868263,
      "learning_rate": 1.2395277334996045e-05,
      "loss": 0.0209,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9426666666666667,
      "eval_loss": 0.2229657918214798,
      "eval_runtime": 6.8676,
      "eval_samples_per_second": 546.045,
      "eval_steps_per_second": 8.591,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.018096923828125,
      "learning_rate": 7.500000000000004e-06,
      "loss": 0.0115,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9448,
      "eval_loss": 0.2170349806547165,
      "eval_runtime": 7.0776,
      "eval_samples_per_second": 529.84,
      "eval_steps_per_second": 8.336,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 3.519446655599853e-06,
      "loss": 0.0071,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9466666666666667,
      "eval_loss": 0.21504658460617065,
      "eval_runtime": 6.8235,
      "eval_samples_per_second": 549.57,
      "eval_steps_per_second": 8.647,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.2378636598587036,
      "learning_rate": 9.099962490342784e-07,
      "loss": 0.0057,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.22092002630233765,
      "eval_runtime": 7.0763,
      "eval_samples_per_second": 529.937,
      "eval_steps_per_second": 8.338,
      "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
}