Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0605

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0605
File size: 3,161 Bytes 
24cbd6d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8477333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0605/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": 9e-05,
      "loss": 0.9847,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8237333333333333,
      "eval_loss": 0.5979694724082947,
      "eval_runtime": 13.4405,
      "eval_samples_per_second": 279.007,
      "eval_steps_per_second": 4.39,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.289999008178711,
      "learning_rate": 9e-05,
      "loss": 0.3754,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8301333333333333,
      "eval_loss": 0.567988395690918,
      "eval_runtime": 13.4356,
      "eval_samples_per_second": 279.109,
      "eval_steps_per_second": 4.391,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.264,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8344,
      "eval_loss": 0.5742139220237732,
      "eval_runtime": 13.4279,
      "eval_samples_per_second": 279.268,
      "eval_steps_per_second": 4.394,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.24597753584384918,
      "learning_rate": 9e-05,
      "loss": 0.1956,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8346666666666667,
      "eval_loss": 0.5894019603729248,
      "eval_runtime": 12.7872,
      "eval_samples_per_second": 293.263,
      "eval_steps_per_second": 4.614,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 149.62738037109375,
      "learning_rate": 9e-05,
      "loss": 0.1703,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8434666666666667,
      "eval_loss": 0.6213681101799011,
      "eval_runtime": 13.3831,
      "eval_samples_per_second": 280.205,
      "eval_steps_per_second": 4.409,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2916773557662964,
      "learning_rate": 9e-05,
      "loss": 0.1439,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8477333333333333,
      "eval_loss": 0.6060090065002441,
      "eval_runtime": 12.8244,
      "eval_samples_per_second": 292.412,
      "eval_steps_per_second": 4.601,
      "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
}