Hugging Face's logo

ProbeX
/
Model-J__SupViT__model_idx_0272

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__SupViT__model_idx_0272
File size: 4,043 Bytes 
57aa99e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9552,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0272/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": 0.4249539077281952,
      "learning_rate": 8.728616793536588e-05,
      "loss": 0.6115,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9282666666666667,
      "eval_loss": 0.24335192143917084,
      "eval_runtime": 10.6779,
      "eval_samples_per_second": 351.194,
      "eval_steps_per_second": 5.525,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2850126028060913,
      "learning_rate": 7.947199994035401e-05,
      "loss": 0.1157,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9325333333333333,
      "eval_loss": 0.24012009799480438,
      "eval_runtime": 11.2356,
      "eval_samples_per_second": 333.759,
      "eval_steps_per_second": 5.251,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.013195399194955826,
      "learning_rate": 6.75e-05,
      "loss": 0.0512,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9461333333333334,
      "eval_loss": 0.22177687287330627,
      "eval_runtime": 10.7006,
      "eval_samples_per_second": 350.449,
      "eval_steps_per_second": 5.514,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.812760353088379,
      "learning_rate": 5.2814167995011876e-05,
      "loss": 0.024,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9442666666666667,
      "eval_loss": 0.22884798049926758,
      "eval_runtime": 11.1062,
      "eval_samples_per_second": 337.649,
      "eval_steps_per_second": 5.312,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2465815544128418,
      "learning_rate": 3.7185832004988136e-05,
      "loss": 0.0088,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.952,
      "eval_loss": 0.1972501426935196,
      "eval_runtime": 11.0383,
      "eval_samples_per_second": 339.726,
      "eval_steps_per_second": 5.345,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.021491989493370056,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.0029,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.952,
      "eval_loss": 0.20399931073188782,
      "eval_runtime": 10.5512,
      "eval_samples_per_second": 355.41,
      "eval_steps_per_second": 5.592,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.055833996679956e-05,
      "loss": 0.001,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9522666666666667,
      "eval_loss": 0.20679543912410736,
      "eval_runtime": 10.6109,
      "eval_samples_per_second": 353.411,
      "eval_steps_per_second": 5.56,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.007667860481888056,
      "learning_rate": 2.7299887471028354e-06,
      "loss": 0.0008,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9552,
      "eval_loss": 0.20396152138710022,
      "eval_runtime": 10.8267,
      "eval_samples_per_second": 346.365,
      "eval_steps_per_second": 5.449,
      "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
}