Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0749

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0749
File size: 3,252 Bytes 
d861752
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9218666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0749/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": 8.562221064561357e-05,
      "loss": 0.9208,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8434666666666667,
      "eval_loss": 0.5051745176315308,
      "eval_runtime": 12.6047,
      "eval_samples_per_second": 297.509,
      "eval_steps_per_second": 4.681,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4513640403747559,
      "learning_rate": 7.319906209778102e-05,
      "loss": 0.3254,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.4421617388725281,
      "eval_runtime": 12.6594,
      "eval_samples_per_second": 296.223,
      "eval_steps_per_second": 4.661,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.37082356214523315,
      "learning_rate": 5.5190743462682014e-05,
      "loss": 0.1728,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8776,
      "eval_loss": 0.40934687852859497,
      "eval_runtime": 12.6825,
      "eval_samples_per_second": 295.683,
      "eval_steps_per_second": 4.652,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.00931170117110014,
      "learning_rate": 3.516402310353216e-05,
      "loss": 0.0805,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8904,
      "eval_loss": 0.4118105471134186,
      "eval_runtime": 12.5186,
      "eval_samples_per_second": 299.553,
      "eval_steps_per_second": 4.713,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0038332073017954826,
      "learning_rate": 1.708543859906803e-05,
      "loss": 0.0275,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9168,
      "eval_loss": 0.32130905985832214,
      "eval_runtime": 12.8441,
      "eval_samples_per_second": 291.963,
      "eval_steps_per_second": 4.594,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.28254812955856323,
      "learning_rate": 4.53567532968734e-06,
      "loss": 0.006,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9218666666666666,
      "eval_loss": 0.31718909740448,
      "eval_runtime": 13.5819,
      "eval_samples_per_second": 276.103,
      "eval_steps_per_second": 4.344,
      "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
}