Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0118

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0118
File size: 3,254 Bytes 
e57f16d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9162666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0118/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": 60.24851608276367,
      "learning_rate": 7.509009009009009e-05,
      "loss": 0.9079,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8298666666666666,
      "eval_loss": 0.5302360653877258,
      "eval_runtime": 12.5546,
      "eval_samples_per_second": 298.696,
      "eval_steps_per_second": 4.699,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7263413071632385,
      "learning_rate": 6.00900900900901e-05,
      "loss": 0.2949,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.4558745324611664,
      "eval_runtime": 12.3167,
      "eval_samples_per_second": 304.466,
      "eval_steps_per_second": 4.79,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7926903367042542,
      "learning_rate": 4.509009009009009e-05,
      "loss": 0.1409,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8808,
      "eval_loss": 0.443220317363739,
      "eval_runtime": 12.2549,
      "eval_samples_per_second": 306.001,
      "eval_steps_per_second": 4.814,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.5155771970748901,
      "learning_rate": 3.0090090090090093e-05,
      "loss": 0.0637,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8984,
      "eval_loss": 0.3752800226211548,
      "eval_runtime": 12.6605,
      "eval_samples_per_second": 296.196,
      "eval_steps_per_second": 4.66,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.007071063853800297,
      "learning_rate": 1.5090090090090091e-05,
      "loss": 0.0241,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9010666666666667,
      "eval_loss": 0.393775999546051,
      "eval_runtime": 13.3624,
      "eval_samples_per_second": 280.637,
      "eval_steps_per_second": 4.415,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.37470248341560364,
      "learning_rate": 9.00900900900901e-08,
      "loss": 0.0043,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9162666666666667,
      "eval_loss": 0.3449421226978302,
      "eval_runtime": 12.3638,
      "eval_samples_per_second": 303.305,
      "eval_steps_per_second": 4.772,
      "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
}