Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0421

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0421
File size: 3,683 Bytes 
b94aa79
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9501333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0421/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 8.730227815298347e-05,
      "loss": 0.6659,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9218666666666666,
      "eval_loss": 0.26029619574546814,
      "eval_runtime": 13.5216,
      "eval_samples_per_second": 277.334,
      "eval_steps_per_second": 4.363,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4119769334793091,
      "learning_rate": 7.95023019690139e-05,
      "loss": 0.1558,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9298666666666666,
      "eval_loss": 0.24026884138584137,
      "eval_runtime": 13.2842,
      "eval_samples_per_second": 282.29,
      "eval_steps_per_second": 4.441,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.02847915329039097,
      "learning_rate": 6.75408389678355e-05,
      "loss": 0.0753,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9336,
      "eval_loss": 0.24518296122550964,
      "eval_runtime": 13.2118,
      "eval_samples_per_second": 283.837,
      "eval_steps_per_second": 4.466,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.021600618958473206,
      "learning_rate": 5.286061811978304e-05,
      "loss": 0.0403,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9362666666666667,
      "eval_loss": 0.24746812880039215,
      "eval_runtime": 13.1567,
      "eval_samples_per_second": 285.026,
      "eval_steps_per_second": 4.484,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.026628440245985985,
      "learning_rate": 3.723229071611673e-05,
      "loss": 0.0158,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9381333333333334,
      "eval_loss": 0.25851473212242126,
      "eval_runtime": 13.2406,
      "eval_samples_per_second": 283.22,
      "eval_steps_per_second": 4.456,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04213137552142143,
      "learning_rate": 2.2540863691266368e-05,
      "loss": 0.0071,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9448,
      "eval_loss": 0.25095584988594055,
      "eval_runtime": 13.2678,
      "eval_samples_per_second": 282.639,
      "eval_steps_per_second": 4.447,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.042094212025403976,
      "learning_rate": 1.055833996679956e-05,
      "loss": 0.0033,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9501333333333334,
      "eval_loss": 0.21870119869709015,
      "eval_runtime": 13.1291,
      "eval_samples_per_second": 285.624,
      "eval_steps_per_second": 4.494,
      "step": 2331
    }
  ],
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}