Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0906

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0906
File size: 3,931 Bytes 
b726e19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3218666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0906/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": 20.424713134765625,
      "learning_rate": 0.0005,
      "loss": 3.5184,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.13493333333333332,
      "eval_loss": 3.3105854988098145,
      "eval_runtime": 11.3223,
      "eval_samples_per_second": 331.205,
      "eval_steps_per_second": 5.211,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 17.400487899780273,
      "learning_rate": 0.0005,
      "loss": 3.0127,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.21466666666666667,
      "eval_loss": 2.969465732574463,
      "eval_runtime": 11.3283,
      "eval_samples_per_second": 331.03,
      "eval_steps_per_second": 5.208,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.02628517150879,
      "learning_rate": 0.0005,
      "loss": 2.8517,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.24346666666666666,
      "eval_loss": 2.834296703338623,
      "eval_runtime": 11.0749,
      "eval_samples_per_second": 338.603,
      "eval_steps_per_second": 5.327,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.06322479248047,
      "learning_rate": 0.0005,
      "loss": 2.7407,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2752,
      "eval_loss": 2.7106635570526123,
      "eval_runtime": 11.3164,
      "eval_samples_per_second": 331.378,
      "eval_steps_per_second": 5.214,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 15.770452499389648,
      "learning_rate": 0.0005,
      "loss": 2.6392,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2608,
      "eval_loss": 2.734571933746338,
      "eval_runtime": 11.073,
      "eval_samples_per_second": 338.662,
      "eval_steps_per_second": 5.328,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.157583236694336,
      "learning_rate": 0.0005,
      "loss": 2.5457,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2832,
      "eval_loss": 2.604435443878174,
      "eval_runtime": 11.2207,
      "eval_samples_per_second": 334.204,
      "eval_steps_per_second": 5.258,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.4667,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.32026666666666664,
      "eval_loss": 2.4892709255218506,
      "eval_runtime": 11.6107,
      "eval_samples_per_second": 322.978,
      "eval_steps_per_second": 5.082,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 7.9352264404296875,
      "learning_rate": 0.0005,
      "loss": 2.3804,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3218666666666667,
      "eval_loss": 2.5072476863861084,
      "eval_runtime": 11.0621,
      "eval_samples_per_second": 338.996,
      "eval_steps_per_second": 5.334,
      "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
}