Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0239

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0239
File size: 3,666 Bytes 
3829043
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.44053333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0239/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": 19.988658905029297,
      "learning_rate": 0.0002575289575289575,
      "loss": 3.4194,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20106666666666667,
      "eval_loss": 3.0035719871520996,
      "eval_runtime": 13.3949,
      "eval_samples_per_second": 279.957,
      "eval_steps_per_second": 4.405,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.69977569580078,
      "learning_rate": 0.00021467181467181467,
      "loss": 2.8422,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.25626666666666664,
      "eval_loss": 2.7517385482788086,
      "eval_runtime": 13.3814,
      "eval_samples_per_second": 280.239,
      "eval_steps_per_second": 4.409,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 21.09208106994629,
      "learning_rate": 0.0001718146718146718,
      "loss": 2.5485,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3312,
      "eval_loss": 2.478869676589966,
      "eval_runtime": 13.1293,
      "eval_samples_per_second": 285.622,
      "eval_steps_per_second": 4.494,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 35.67688751220703,
      "learning_rate": 0.00012895752895752895,
      "loss": 2.2754,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3456,
      "eval_loss": 2.3722901344299316,
      "eval_runtime": 13.4414,
      "eval_samples_per_second": 278.989,
      "eval_steps_per_second": 4.389,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 27.166015625,
      "learning_rate": 8.61003861003861e-05,
      "loss": 2.0611,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.40053333333333335,
      "eval_loss": 2.1474244594573975,
      "eval_runtime": 13.362,
      "eval_samples_per_second": 280.647,
      "eval_steps_per_second": 4.416,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 32.45797348022461,
      "learning_rate": 4.324324324324324e-05,
      "loss": 1.8199,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4226666666666667,
      "eval_loss": 2.0862293243408203,
      "eval_runtime": 13.6206,
      "eval_samples_per_second": 275.317,
      "eval_steps_per_second": 4.332,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 37.14344024658203,
      "learning_rate": 3.861003861003861e-07,
      "loss": 1.5751,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.44053333333333333,
      "eval_loss": 2.0469608306884766,
      "eval_runtime": 13.4826,
      "eval_samples_per_second": 278.137,
      "eval_steps_per_second": 4.376,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}