Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0320

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0320
File size: 2,857 Bytes 
2643d55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.3834666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0320/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00040120120120120116,
      "loss": 3.4244,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19333333333333333,
      "eval_loss": 2.9812798500061035,
      "eval_runtime": 8.128,
      "eval_samples_per_second": 461.367,
      "eval_steps_per_second": 7.259,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 20.02377700805664,
      "learning_rate": 0.0003012012012012012,
      "loss": 2.8586,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.24533333333333332,
      "eval_loss": 2.808511734008789,
      "eval_runtime": 6.0457,
      "eval_samples_per_second": 620.275,
      "eval_steps_per_second": 9.759,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 22.170238494873047,
      "learning_rate": 0.0002012012012012012,
      "loss": 2.6245,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3101333333333333,
      "eval_loss": 2.5484375953674316,
      "eval_runtime": 6.5601,
      "eval_samples_per_second": 571.639,
      "eval_steps_per_second": 8.994,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 24.414812088012695,
      "learning_rate": 0.0001012012012012012,
      "loss": 2.4015,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.368,
      "eval_loss": 2.3500008583068848,
      "eval_runtime": 6.3503,
      "eval_samples_per_second": 590.519,
      "eval_steps_per_second": 9.291,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 34.07997512817383,
      "learning_rate": 1.201201201201201e-06,
      "loss": 2.1585,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3834666666666667,
      "eval_loss": 2.231992483139038,
      "eval_runtime": 5.9191,
      "eval_samples_per_second": 633.544,
      "eval_steps_per_second": 9.968,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}