Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0350

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0350
File size: 4,021 Bytes 
2480d57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9496,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0350/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": 3.59938645362854,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.8316,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9304,
      "eval_loss": 0.264137327671051,
      "eval_runtime": 8.8852,
      "eval_samples_per_second": 422.051,
      "eval_steps_per_second": 6.64,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 9.683337211608887,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.1572,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9312,
      "eval_loss": 0.2312602549791336,
      "eval_runtime": 7.4533,
      "eval_samples_per_second": 503.131,
      "eval_steps_per_second": 7.916,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5272884964942932,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0773,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9349333333333333,
      "eval_loss": 0.23084141314029694,
      "eval_runtime": 7.5224,
      "eval_samples_per_second": 498.512,
      "eval_steps_per_second": 7.843,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.03195216506719589,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 0.0396,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9381333333333334,
      "eval_loss": 0.2297796905040741,
      "eval_runtime": 7.5564,
      "eval_samples_per_second": 496.27,
      "eval_steps_per_second": 7.808,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.02192077226936817,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.0179,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9453333333333334,
      "eval_loss": 0.21872910857200623,
      "eval_runtime": 7.503,
      "eval_samples_per_second": 499.803,
      "eval_steps_per_second": 7.864,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.024353234097361565,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0084,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9424,
      "eval_loss": 0.22383655607700348,
      "eval_runtime": 7.2855,
      "eval_samples_per_second": 514.724,
      "eval_steps_per_second": 8.098,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 5.865744425999756e-06,
      "loss": 0.0037,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9472,
      "eval_loss": 0.22158749401569366,
      "eval_runtime": 7.3866,
      "eval_samples_per_second": 507.674,
      "eval_steps_per_second": 7.987,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.02885887213051319,
      "learning_rate": 1.5166604150571306e-06,
      "loss": 0.0028,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9496,
      "eval_loss": 0.2235015332698822,
      "eval_runtime": 7.3684,
      "eval_samples_per_second": 508.928,
      "eval_steps_per_second": 8.007,
      "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
}