Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0433

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0433
File size: 3,269 Bytes 
6151a15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9402666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0433/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": 4.996685981750488,
      "learning_rate": 2.85232922088503e-05,
      "loss": 0.8375,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.4073767066001892,
      "eval_runtime": 6.0046,
      "eval_samples_per_second": 624.519,
      "eval_steps_per_second": 9.826,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 33.363365173339844,
      "learning_rate": 2.4368144166557088e-05,
      "loss": 0.2223,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9024,
      "eval_loss": 0.30470696091651917,
      "eval_runtime": 5.8577,
      "eval_samples_per_second": 640.188,
      "eval_steps_per_second": 10.072,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.314783096313477,
      "learning_rate": 1.8357520279328874e-05,
      "loss": 0.0935,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.27348756790161133,
      "eval_runtime": 5.9123,
      "eval_samples_per_second": 634.27,
      "eval_steps_per_second": 9.979,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.06691589951515198,
      "learning_rate": 1.1681898323495617e-05,
      "loss": 0.0342,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.924,
      "eval_loss": 0.2869836688041687,
      "eval_runtime": 6.3262,
      "eval_samples_per_second": 592.769,
      "eval_steps_per_second": 9.326,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5284973382949829,
      "learning_rate": 5.6634670985405755e-06,
      "loss": 0.0104,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9301333333333334,
      "eval_loss": 0.2606372833251953,
      "eval_runtime": 6.1649,
      "eval_samples_per_second": 608.286,
      "eval_steps_per_second": 9.57,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.024342846125364304,
      "learning_rate": 1.4942507197812133e-06,
      "loss": 0.0039,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9402666666666667,
      "eval_loss": 0.24347154796123505,
      "eval_runtime": 6.2343,
      "eval_samples_per_second": 601.512,
      "eval_steps_per_second": 9.464,
      "step": 1998
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}