Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0663

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0663
File size: 3,671 Bytes 
0df5f97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9058666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0663/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": 3.3649775981903076,
      "learning_rate": 0.0004809698831278217,
      "loss": 0.8793,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8058666666666666,
      "eval_loss": 0.647365927696228,
      "eval_runtime": 4.8126,
      "eval_samples_per_second": 779.202,
      "eval_steps_per_second": 12.259,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0004269850409335979,
      "loss": 0.5141,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8336,
      "eval_loss": 0.5677223801612854,
      "eval_runtime": 4.8934,
      "eval_samples_per_second": 766.333,
      "eval_steps_per_second": 12.057,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.168091773986816,
      "learning_rate": 0.0003459431688641196,
      "loss": 0.3481,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5193018317222595,
      "eval_runtime": 5.0333,
      "eval_samples_per_second": 745.042,
      "eval_steps_per_second": 11.722,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.371315956115723,
      "learning_rate": 0.00025029481906207064,
      "loss": 0.2079,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8514666666666667,
      "eval_loss": 0.5326263904571533,
      "eval_runtime": 4.7356,
      "eval_samples_per_second": 791.881,
      "eval_steps_per_second": 12.459,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.02506338246166706,
      "learning_rate": 0.00015460158573036287,
      "loss": 0.1105,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.4590805470943451,
      "eval_runtime": 4.7995,
      "eval_samples_per_second": 781.334,
      "eval_steps_per_second": 12.293,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 5.047616004943848,
      "learning_rate": 7.343189618242854e-05,
      "loss": 0.0457,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.416449636220932,
      "eval_runtime": 4.8804,
      "eval_samples_per_second": 768.377,
      "eval_steps_per_second": 12.089,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.832478642463684,
      "learning_rate": 1.9143099846872597e-05,
      "loss": 0.0153,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9058666666666667,
      "eval_loss": 0.38776344060897827,
      "eval_runtime": 4.8618,
      "eval_samples_per_second": 771.313,
      "eval_steps_per_second": 12.135,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}