Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0823

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0823
File size: 3,267 Bytes 
3388ed9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.38133333333333336,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0823/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 16.53816032409668,
      "learning_rate": 0.0004174174174174174,
      "loss": 3.4855,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19306666666666666,
      "eval_loss": 3.109666585922241,
      "eval_runtime": 11.1978,
      "eval_samples_per_second": 334.886,
      "eval_steps_per_second": 5.269,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.07221221923828,
      "learning_rate": 0.0003340840840840841,
      "loss": 2.9237,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2208,
      "eval_loss": 2.8496174812316895,
      "eval_runtime": 10.5335,
      "eval_samples_per_second": 356.008,
      "eval_steps_per_second": 5.601,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.38994789123535,
      "learning_rate": 0.0002507507507507508,
      "loss": 2.6746,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.27066666666666667,
      "eval_loss": 2.6612942218780518,
      "eval_runtime": 10.7304,
      "eval_samples_per_second": 349.475,
      "eval_steps_per_second": 5.498,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.432212829589844,
      "learning_rate": 0.00016741741741741742,
      "loss": 2.4658,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3141333333333333,
      "eval_loss": 2.5042316913604736,
      "eval_runtime": 10.4522,
      "eval_samples_per_second": 358.775,
      "eval_steps_per_second": 5.645,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 25.199064254760742,
      "learning_rate": 8.408408408408409e-05,
      "loss": 2.243,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3448,
      "eval_loss": 2.3947155475616455,
      "eval_runtime": 10.3635,
      "eval_samples_per_second": 361.847,
      "eval_steps_per_second": 5.693,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 27.720495223999023,
      "learning_rate": 7.507507507507508e-07,
      "loss": 2.0033,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.38133333333333336,
      "eval_loss": 2.292445421218872,
      "eval_runtime": 10.8809,
      "eval_samples_per_second": 344.642,
      "eval_steps_per_second": 5.422,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}