Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0551

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0551
File size: 4,049 Bytes 
2d6eb67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8997333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0551/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": 0.7301314473152161,
      "learning_rate": 0.0004809698831278217,
      "loss": 0.8384,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7952,
      "eval_loss": 0.6743485927581787,
      "eval_runtime": 12.4291,
      "eval_samples_per_second": 301.712,
      "eval_steps_per_second": 4.747,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.263650417327881,
      "learning_rate": 0.00042677669529663686,
      "loss": 0.4591,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8221333333333334,
      "eval_loss": 0.6374006867408752,
      "eval_runtime": 12.2585,
      "eval_samples_per_second": 305.911,
      "eval_steps_per_second": 4.813,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.8159643411636353,
      "learning_rate": 0.0003456708580912725,
      "loss": 0.2939,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8301333333333333,
      "eval_loss": 0.6077426075935364,
      "eval_runtime": 12.284,
      "eval_samples_per_second": 305.276,
      "eval_steps_per_second": 4.803,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.23180150985717773,
      "learning_rate": 0.00025,
      "loss": 0.1672,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5668855309486389,
      "eval_runtime": 12.2979,
      "eval_samples_per_second": 304.931,
      "eval_steps_per_second": 4.798,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.01949012652039528,
      "learning_rate": 0.00015432914190872756,
      "loss": 0.0772,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.868,
      "eval_loss": 0.5301832556724548,
      "eval_runtime": 12.2352,
      "eval_samples_per_second": 306.493,
      "eval_steps_per_second": 4.822,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.06045107543468475,
      "learning_rate": 7.322330470336314e-05,
      "loss": 0.0185,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8941333333333333,
      "eval_loss": 0.4366999864578247,
      "eval_runtime": 12.3114,
      "eval_samples_per_second": 304.597,
      "eval_steps_per_second": 4.792,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.9143099846872597e-05,
      "loss": 0.0037,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8984,
      "eval_loss": 0.42928996682167053,
      "eval_runtime": 12.2026,
      "eval_samples_per_second": 307.312,
      "eval_steps_per_second": 4.835,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0032204780727624893,
      "learning_rate": 1.7383661915504333e-10,
      "loss": 0.0016,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8997333333333334,
      "eval_loss": 0.428939551115036,
      "eval_runtime": 12.454,
      "eval_samples_per_second": 301.108,
      "eval_steps_per_second": 4.737,
      "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
}