Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0494

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0494
File size: 3,280 Bytes 
05b386d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9130666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0494/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": 4.111772537231445,
      "learning_rate": 8.404170694504206e-05,
      "loss": 0.8829,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8109333333333333,
      "eval_loss": 0.6089245080947876,
      "eval_runtime": 7.6256,
      "eval_samples_per_second": 491.763,
      "eval_steps_per_second": 7.737,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.450563907623291,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.3188,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8341333333333333,
      "eval_loss": 0.5561917424201965,
      "eval_runtime": 7.5142,
      "eval_samples_per_second": 499.058,
      "eval_steps_per_second": 7.852,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.021362116560339928,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.153,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8682666666666666,
      "eval_loss": 0.46703916788101196,
      "eval_runtime": 7.4006,
      "eval_samples_per_second": 506.714,
      "eval_steps_per_second": 7.972,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 51.5447883605957,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.0683,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9024,
      "eval_loss": 0.34464943408966064,
      "eval_runtime": 7.244,
      "eval_samples_per_second": 517.67,
      "eval_steps_per_second": 8.145,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.004849608056247234,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0204,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.3225628137588501,
      "eval_runtime": 7.6415,
      "eval_samples_per_second": 490.742,
      "eval_steps_per_second": 7.721,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00045165017945691943,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0041,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9130666666666667,
      "eval_loss": 0.33044329285621643,
      "eval_runtime": 8.3938,
      "eval_samples_per_second": 446.759,
      "eval_steps_per_second": 7.029,
      "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
}