Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0028

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0028
File size: 3,643 Bytes 
a83e066
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.4053333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0028/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 0.0004758237055481881,
      "loss": 3.3621,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17786666666666667,
      "eval_loss": 3.0707900524139404,
      "eval_runtime": 6.3362,
      "eval_samples_per_second": 591.835,
      "eval_steps_per_second": 9.312,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.030057907104492,
      "learning_rate": 0.00040692388948875507,
      "loss": 2.8533,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2541333333333333,
      "eval_loss": 2.796761989593506,
      "eval_runtime": 6.4234,
      "eval_samples_per_second": 583.799,
      "eval_steps_per_second": 9.185,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 28.893508911132812,
      "learning_rate": 0.0003069433725708678,
      "loss": 2.6403,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2936,
      "eval_loss": 2.5495879650115967,
      "eval_runtime": 7.0142,
      "eval_samples_per_second": 534.633,
      "eval_steps_per_second": 8.412,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 28.444795608520508,
      "learning_rate": 0.0001956845223506859,
      "loss": 2.4093,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.32826666666666665,
      "eval_loss": 2.417494773864746,
      "eval_runtime": 6.9846,
      "eval_samples_per_second": 536.896,
      "eval_steps_per_second": 8.447,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.619653701782227,
      "learning_rate": 9.518351861456881e-05,
      "loss": 2.1686,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.372,
      "eval_loss": 2.272111177444458,
      "eval_runtime": 6.4377,
      "eval_samples_per_second": 582.509,
      "eval_steps_per_second": 9.165,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 19.411657333374023,
      "learning_rate": 2.5345817716378312e-05,
      "loss": 1.9225,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.396,
      "eval_loss": 2.1750853061676025,
      "eval_runtime": 6.5208,
      "eval_samples_per_second": 575.079,
      "eval_steps_per_second": 9.048,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 15.783188819885254,
      "learning_rate": 3.6328221945103325e-09,
      "loss": 1.7219,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4053333333333333,
      "eval_loss": 2.178642749786377,
      "eval_runtime": 6.6836,
      "eval_samples_per_second": 561.073,
      "eval_steps_per_second": 8.828,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}