Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0830

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0830
File size: 3,180 Bytes 
df3b0a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.32266666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0830/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": Infinity,
      "learning_rate": 0.0005,
      "loss": 3.3663,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2008,
      "eval_loss": 3.0195043087005615,
      "eval_runtime": 12.1377,
      "eval_samples_per_second": 308.956,
      "eval_steps_per_second": 4.861,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 16.826833724975586,
      "learning_rate": 0.0005,
      "loss": 2.8903,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.22693333333333332,
      "eval_loss": 2.8448686599731445,
      "eval_runtime": 11.8441,
      "eval_samples_per_second": 316.614,
      "eval_steps_per_second": 4.981,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.47182846069336,
      "learning_rate": 0.0005,
      "loss": 2.7481,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.22986666666666666,
      "eval_loss": 2.8344151973724365,
      "eval_runtime": 10.9369,
      "eval_samples_per_second": 342.877,
      "eval_steps_per_second": 5.395,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 24.28130340576172,
      "learning_rate": 0.0005,
      "loss": 2.6118,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.28746666666666665,
      "eval_loss": 2.60884690284729,
      "eval_runtime": 11.0967,
      "eval_samples_per_second": 337.939,
      "eval_steps_per_second": 5.317,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.028762817382812,
      "learning_rate": 0.0005,
      "loss": 2.5106,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.29413333333333336,
      "eval_loss": 2.5138773918151855,
      "eval_runtime": 10.7556,
      "eval_samples_per_second": 348.655,
      "eval_steps_per_second": 5.485,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 17.70652198791504,
      "learning_rate": 0.0005,
      "loss": 2.424,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.32266666666666666,
      "eval_loss": 2.4449353218078613,
      "eval_runtime": 10.8243,
      "eval_samples_per_second": 346.444,
      "eval_steps_per_second": 5.451,
      "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
}