Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0144

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0144
File size: 4,002 Bytes 
49fe58f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9530666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0144/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": 0.5626757144927979,
      "learning_rate": 7.875e-05,
      "loss": 0.5696,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9336,
      "eval_loss": 0.23624810576438904,
      "eval_runtime": 5.964,
      "eval_samples_per_second": 628.769,
      "eval_steps_per_second": 9.893,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.06620332598686218,
      "learning_rate": 6.75e-05,
      "loss": 0.1071,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9317333333333333,
      "eval_loss": 0.2223302572965622,
      "eval_runtime": 5.8373,
      "eval_samples_per_second": 642.423,
      "eval_steps_per_second": 10.107,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.10265876352787018,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 0.0453,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.2576395869255066,
      "eval_runtime": 5.8948,
      "eval_samples_per_second": 636.153,
      "eval_steps_per_second": 10.009,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05127749592065811,
      "learning_rate": 4.5e-05,
      "loss": 0.0169,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.23558522760868073,
      "eval_runtime": 5.8425,
      "eval_samples_per_second": 641.85,
      "eval_steps_per_second": 10.098,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.010233158245682716,
      "learning_rate": 3.375e-05,
      "loss": 0.0064,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.236871138215065,
      "eval_runtime": 6.8134,
      "eval_samples_per_second": 550.382,
      "eval_steps_per_second": 8.659,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.010609577409923077,
      "learning_rate": 2.25e-05,
      "loss": 0.0031,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.22287249565124512,
      "eval_runtime": 5.8613,
      "eval_samples_per_second": 639.788,
      "eval_steps_per_second": 10.066,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.1283783783783785e-05,
      "loss": 0.0018,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9512,
      "eval_loss": 0.22152727842330933,
      "eval_runtime": 5.9952,
      "eval_samples_per_second": 625.505,
      "eval_steps_per_second": 9.841,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.06503234803676605,
      "learning_rate": 3.3783783783783786e-08,
      "loss": 0.0011,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9530666666666666,
      "eval_loss": 0.21593619883060455,
      "eval_runtime": 6.7916,
      "eval_samples_per_second": 552.149,
      "eval_steps_per_second": 8.687,
      "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
}