Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0147

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0147
File size: 4,067 Bytes 
7381efd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9616,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0147/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": 0.22032923996448517,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.5863,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.928,
      "eval_loss": 0.26772239804267883,
      "eval_runtime": 6.4952,
      "eval_samples_per_second": 577.352,
      "eval_steps_per_second": 9.084,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.25858816504478455,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.1298,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.2256719470024109,
      "eval_runtime": 6.4086,
      "eval_samples_per_second": 585.153,
      "eval_steps_per_second": 9.206,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.032304201275110245,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0677,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9498666666666666,
      "eval_loss": 0.18359023332595825,
      "eval_runtime": 6.5184,
      "eval_samples_per_second": 575.293,
      "eval_steps_per_second": 9.051,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.010900559835135937,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.0351,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9522666666666667,
      "eval_loss": 0.1691388338804245,
      "eval_runtime": 6.3743,
      "eval_samples_per_second": 588.295,
      "eval_steps_per_second": 9.256,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.016635043546557426,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.0169,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9578666666666666,
      "eval_loss": 0.17128410935401917,
      "eval_runtime": 6.4622,
      "eval_samples_per_second": 580.294,
      "eval_steps_per_second": 9.13,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.008960281498730183,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0083,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9549333333333333,
      "eval_loss": 0.18995113670825958,
      "eval_runtime": 6.6636,
      "eval_samples_per_second": 562.761,
      "eval_steps_per_second": 8.854,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 2.225558892225559e-05,
      "loss": 0.005,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9581333333333333,
      "eval_loss": 0.17419496178627014,
      "eval_runtime": 6.4202,
      "eval_samples_per_second": 584.093,
      "eval_steps_per_second": 9.19,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.005244110245257616,
      "learning_rate": 1.1144477811144478e-05,
      "loss": 0.0029,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9616,
      "eval_loss": 0.16844968497753143,
      "eval_runtime": 6.3765,
      "eval_samples_per_second": 588.101,
      "eval_steps_per_second": 9.253,
      "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
}