Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0416

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0416
File size: 2,855 Bytes 
f5c705b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.41413333333333335,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0416/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": 31.041790008544922,
      "learning_rate": 0.00024054054054054052,
      "loss": 3.3212,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2192,
      "eval_loss": 2.9369354248046875,
      "eval_runtime": 6.7623,
      "eval_samples_per_second": 554.547,
      "eval_steps_per_second": 8.725,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 24.06324005126953,
      "learning_rate": 0.0001805405405405405,
      "loss": 2.7249,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.276,
      "eval_loss": 2.659590721130371,
      "eval_runtime": 6.7692,
      "eval_samples_per_second": 553.98,
      "eval_steps_per_second": 8.716,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 28.121068954467773,
      "learning_rate": 0.00012054054054054053,
      "loss": 2.4184,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.33866666666666667,
      "eval_loss": 2.3708136081695557,
      "eval_runtime": 6.8555,
      "eval_samples_per_second": 547.007,
      "eval_steps_per_second": 8.606,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 40.66616439819336,
      "learning_rate": 6.054054054054053e-05,
      "loss": 2.1096,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.37653333333333333,
      "eval_loss": 2.281187057495117,
      "eval_runtime": 7.124,
      "eval_samples_per_second": 526.389,
      "eval_steps_per_second": 8.282,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 61.614654541015625,
      "learning_rate": 5.405405405405405e-07,
      "loss": 1.7327,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.41413333333333335,
      "eval_loss": 2.1570258140563965,
      "eval_runtime": 6.801,
      "eval_samples_per_second": 551.39,
      "eval_steps_per_second": 8.675,
      "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
}