Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0457

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0457
File size: 2,886 Bytes 
d8a265f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.42533333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0457/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": 23.63539695739746,
      "learning_rate": 0.00027184967850358286,
      "loss": 3.3491,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19493333333333332,
      "eval_loss": 3.0351462364196777,
      "eval_runtime": 7.5637,
      "eval_samples_per_second": 495.786,
      "eval_steps_per_second": 7.8,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.62554931640625,
      "learning_rate": 0.00019715932444832964,
      "loss": 2.7516,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2965333333333333,
      "eval_loss": 2.598407745361328,
      "eval_runtime": 6.2336,
      "eval_samples_per_second": 601.577,
      "eval_steps_per_second": 9.465,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.961456298828125,
      "learning_rate": 0.00010445571134029838,
      "loss": 2.3945,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3602666666666667,
      "eval_loss": 2.3423073291778564,
      "eval_runtime": 7.092,
      "eval_samples_per_second": 528.763,
      "eval_steps_per_second": 8.319,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 21.184215545654297,
      "learning_rate": 2.9148468506836763e-05,
      "loss": 2.0405,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.40826666666666667,
      "eval_loss": 2.148573398590088,
      "eval_runtime": 5.6634,
      "eval_samples_per_second": 662.147,
      "eval_steps_per_second": 10.418,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 25.000890731811523,
      "learning_rate": 2.4031112851152778e-09,
      "loss": 1.7083,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.42533333333333334,
      "eval_loss": 2.1380934715270996,
      "eval_runtime": 5.7234,
      "eval_samples_per_second": 655.201,
      "eval_steps_per_second": 10.308,
      "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
}