Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0930

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0930
File size: 3,941 Bytes 
27c6438
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8197333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0930/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": 0.2745540142059326,
      "learning_rate": 0.0005,
      "loss": 0.8249,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.804,
      "eval_loss": 0.6460326910018921,
      "eval_runtime": 6.5061,
      "eval_samples_per_second": 576.385,
      "eval_steps_per_second": 9.068,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6272382736206055,
      "learning_rate": 0.0005,
      "loss": 0.4929,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.816,
      "eval_loss": 0.6893879175186157,
      "eval_runtime": 6.5676,
      "eval_samples_per_second": 570.987,
      "eval_steps_per_second": 8.984,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 0.3922,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8133333333333334,
      "eval_loss": 0.7171464562416077,
      "eval_runtime": 6.7664,
      "eval_samples_per_second": 554.213,
      "eval_steps_per_second": 8.72,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5647403597831726,
      "learning_rate": 0.0005,
      "loss": 0.3288,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8181333333333334,
      "eval_loss": 0.6869505047798157,
      "eval_runtime": 6.6347,
      "eval_samples_per_second": 565.212,
      "eval_steps_per_second": 8.893,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.6077433824539185,
      "learning_rate": 0.0005,
      "loss": 0.2826,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8165333333333333,
      "eval_loss": 0.7099630236625671,
      "eval_runtime": 6.8417,
      "eval_samples_per_second": 548.112,
      "eval_steps_per_second": 8.624,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 34.136192321777344,
      "learning_rate": 0.0005,
      "loss": 0.2579,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8093333333333333,
      "eval_loss": 0.7130383849143982,
      "eval_runtime": 6.8355,
      "eval_samples_per_second": 548.604,
      "eval_steps_per_second": 8.631,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.01141686923801899,
      "learning_rate": 0.0005,
      "loss": 0.2246,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8122666666666667,
      "eval_loss": 0.730060875415802,
      "eval_runtime": 6.4863,
      "eval_samples_per_second": 578.141,
      "eval_steps_per_second": 9.096,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 12.180059432983398,
      "learning_rate": 0.0005,
      "loss": 0.2057,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8197333333333333,
      "eval_loss": 0.689276933670044,
      "eval_runtime": 6.8521,
      "eval_samples_per_second": 547.28,
      "eval_steps_per_second": 8.611,
      "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
}