Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0960

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0960
File size: 3,904 Bytes 
2345c9f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8136,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0960/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": Infinity,
      "learning_rate": 0.0005,
      "loss": 0.8502,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7877333333333333,
      "eval_loss": 0.7470865845680237,
      "eval_runtime": 14.115,
      "eval_samples_per_second": 265.676,
      "eval_steps_per_second": 4.18,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.961331367492676,
      "learning_rate": 0.0005,
      "loss": 0.505,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8064,
      "eval_loss": 0.6913458108901978,
      "eval_runtime": 12.8518,
      "eval_samples_per_second": 291.789,
      "eval_steps_per_second": 4.591,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 26.01592445373535,
      "learning_rate": 0.0005,
      "loss": 0.3874,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7986666666666666,
      "eval_loss": 0.714604377746582,
      "eval_runtime": 12.97,
      "eval_samples_per_second": 289.13,
      "eval_steps_per_second": 4.549,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.1420547068119049,
      "learning_rate": 0.0005,
      "loss": 0.3228,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8093333333333333,
      "eval_loss": 0.681213915348053,
      "eval_runtime": 12.8638,
      "eval_samples_per_second": 291.516,
      "eval_steps_per_second": 4.587,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 28.49031639099121,
      "learning_rate": 0.0005,
      "loss": 0.2695,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.812,
      "eval_loss": 0.7074100971221924,
      "eval_runtime": 13.0785,
      "eval_samples_per_second": 286.729,
      "eval_steps_per_second": 4.511,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 31.12238121032715,
      "learning_rate": 0.0005,
      "loss": 0.2383,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7965333333333333,
      "eval_loss": 0.8161412477493286,
      "eval_runtime": 13.035,
      "eval_samples_per_second": 287.687,
      "eval_steps_per_second": 4.526,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 15.3955717086792,
      "learning_rate": 0.0005,
      "loss": 0.2242,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8098666666666666,
      "eval_loss": 0.7653522491455078,
      "eval_runtime": 12.8509,
      "eval_samples_per_second": 291.809,
      "eval_steps_per_second": 4.591,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 0.2105,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8136,
      "eval_loss": 0.7128385305404663,
      "eval_runtime": 13.237,
      "eval_samples_per_second": 283.297,
      "eval_steps_per_second": 4.457,
      "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
}