Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0683

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0683
File size: 4,054 Bytes 
d3c3bcd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9064,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0683/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": 0.18496987223625183,
      "learning_rate": 0.0004849231551964771,
      "loss": 0.8596,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8168,
      "eval_loss": 0.6327399611473083,
      "eval_runtime": 12.1853,
      "eval_samples_per_second": 307.748,
      "eval_steps_per_second": 4.842,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4969542622566223,
      "learning_rate": 0.0004415111107797445,
      "loss": 0.4375,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8133333333333334,
      "eval_loss": 0.6385030150413513,
      "eval_runtime": 12.4362,
      "eval_samples_per_second": 301.54,
      "eval_steps_per_second": 4.744,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.11013148725032806,
      "learning_rate": 0.000375,
      "loss": 0.2894,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8413333333333334,
      "eval_loss": 0.5476252436637878,
      "eval_runtime": 12.4494,
      "eval_samples_per_second": 301.219,
      "eval_steps_per_second": 4.739,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.38997790217399597,
      "learning_rate": 0.00029341204441673266,
      "loss": 0.1723,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8493333333333334,
      "eval_loss": 0.5406513214111328,
      "eval_runtime": 12.487,
      "eval_samples_per_second": 300.312,
      "eval_steps_per_second": 4.725,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.015340336598455906,
      "learning_rate": 0.00020658795558326743,
      "loss": 0.0909,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.5698232650756836,
      "eval_runtime": 12.3435,
      "eval_samples_per_second": 303.803,
      "eval_steps_per_second": 4.78,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.010821315459907055,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.0321,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8882666666666666,
      "eval_loss": 0.47416287660598755,
      "eval_runtime": 12.3324,
      "eval_samples_per_second": 304.076,
      "eval_steps_per_second": 4.784,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 5.8657444259997555e-05,
      "loss": 0.0081,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9018666666666667,
      "eval_loss": 0.4420299530029297,
      "eval_runtime": 12.603,
      "eval_samples_per_second": 297.549,
      "eval_steps_per_second": 4.681,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.00292829773388803,
      "learning_rate": 1.5166604150571307e-05,
      "loss": 0.0017,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.4201918840408325,
      "eval_runtime": 12.1409,
      "eval_samples_per_second": 308.873,
      "eval_steps_per_second": 4.86,
      "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
}