Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0755

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0755
File size: 4,062 Bytes 
e0a5faa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.952,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0755/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": 0.9693148732185364,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.1492,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.29058924317359924,
      "eval_runtime": 11.491,
      "eval_samples_per_second": 326.343,
      "eval_steps_per_second": 5.134,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.20783324539661407,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.1666,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.22024032473564148,
      "eval_runtime": 11.0285,
      "eval_samples_per_second": 340.03,
      "eval_steps_per_second": 5.35,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.3927321434021,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.0757,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9458666666666666,
      "eval_loss": 0.1995375007390976,
      "eval_runtime": 11.4893,
      "eval_samples_per_second": 326.392,
      "eval_steps_per_second": 5.135,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.585459291934967,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0356,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9450666666666667,
      "eval_loss": 0.20281289517879486,
      "eval_runtime": 11.0559,
      "eval_samples_per_second": 339.186,
      "eval_steps_per_second": 5.337,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.10677102208137512,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0191,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9437333333333333,
      "eval_loss": 0.22464779019355774,
      "eval_runtime": 11.0269,
      "eval_samples_per_second": 340.078,
      "eval_steps_per_second": 5.351,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.559721827507019,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.0115,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9472,
      "eval_loss": 0.215084046125412,
      "eval_runtime": 10.8599,
      "eval_samples_per_second": 345.305,
      "eval_steps_per_second": 5.433,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 6.676676676676677e-06,
      "loss": 0.0076,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9509333333333333,
      "eval_loss": 0.21209292113780975,
      "eval_runtime": 10.9932,
      "eval_samples_per_second": 341.119,
      "eval_steps_per_second": 5.367,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.040960151702165604,
      "learning_rate": 3.3433433433433436e-06,
      "loss": 0.0054,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.952,
      "eval_loss": 0.2060813456773758,
      "eval_runtime": 10.9631,
      "eval_samples_per_second": 342.057,
      "eval_steps_per_second": 5.382,
      "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
}