Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0135

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0135
File size: 3,279 Bytes 
8edabf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9250666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0135/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": 0.7779549956321716,
      "learning_rate": 8.404170694504206e-05,
      "loss": 0.8819,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8437333333333333,
      "eval_loss": 0.4986955225467682,
      "eval_runtime": 5.873,
      "eval_samples_per_second": 638.521,
      "eval_steps_per_second": 10.046,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.483290672302246,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.2918,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8493333333333334,
      "eval_loss": 0.5137752890586853,
      "eval_runtime": 6.2389,
      "eval_samples_per_second": 601.071,
      "eval_steps_per_second": 9.457,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 14.142939567565918,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.1278,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8906666666666667,
      "eval_loss": 0.39263567328453064,
      "eval_runtime": 5.8603,
      "eval_samples_per_second": 639.903,
      "eval_steps_per_second": 10.068,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.912620544433594,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.0445,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9088,
      "eval_loss": 0.351238489151001,
      "eval_runtime": 5.8623,
      "eval_samples_per_second": 639.679,
      "eval_steps_per_second": 10.064,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.19366654753684998,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0089,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9186666666666666,
      "eval_loss": 0.3128499984741211,
      "eval_runtime": 6.4214,
      "eval_samples_per_second": 583.989,
      "eval_steps_per_second": 9.188,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2696741223335266,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0018,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9250666666666667,
      "eval_loss": 0.3053063154220581,
      "eval_runtime": 6.4589,
      "eval_samples_per_second": 580.595,
      "eval_steps_per_second": 9.135,
      "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
}