Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0521

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0521
File size: 4,053 Bytes 
f6e0a85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9138666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0521/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": 7.4716057777404785,
      "learning_rate": 0.0004849231551964771,
      "loss": 0.7574,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8077333333333333,
      "eval_loss": 0.655104398727417,
      "eval_runtime": 12.7095,
      "eval_samples_per_second": 295.055,
      "eval_steps_per_second": 4.642,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6037126779556274,
      "learning_rate": 0.0004415111107797445,
      "loss": 0.4256,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8386666666666667,
      "eval_loss": 0.5512299537658691,
      "eval_runtime": 13.1262,
      "eval_samples_per_second": 285.689,
      "eval_steps_per_second": 4.495,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.01526631135493517,
      "learning_rate": 0.000375,
      "loss": 0.2684,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8554666666666667,
      "eval_loss": 0.5211629867553711,
      "eval_runtime": 13.0804,
      "eval_samples_per_second": 286.689,
      "eval_steps_per_second": 4.511,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3008439540863037,
      "learning_rate": 0.00029341204441673266,
      "loss": 0.1661,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.5389682650566101,
      "eval_runtime": 13.1194,
      "eval_samples_per_second": 285.836,
      "eval_steps_per_second": 4.497,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 16.833465576171875,
      "learning_rate": 0.00020658795558326743,
      "loss": 0.0951,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8808,
      "eval_loss": 0.47957542538642883,
      "eval_runtime": 12.929,
      "eval_samples_per_second": 290.046,
      "eval_steps_per_second": 4.563,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.017864255234599113,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.0294,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8928,
      "eval_loss": 0.4181145429611206,
      "eval_runtime": 12.925,
      "eval_samples_per_second": 290.135,
      "eval_steps_per_second": 4.565,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 5.8657444259997555e-05,
      "loss": 0.0072,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9101333333333333,
      "eval_loss": 0.3901694715023041,
      "eval_runtime": 12.5513,
      "eval_samples_per_second": 298.773,
      "eval_steps_per_second": 4.701,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.022689063102006912,
      "learning_rate": 1.5166604150571307e-05,
      "loss": 0.0017,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9138666666666667,
      "eval_loss": 0.37346670031547546,
      "eval_runtime": 12.4468,
      "eval_samples_per_second": 301.282,
      "eval_steps_per_second": 4.74,
      "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
}