Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0866

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0866
File size: 3,284 Bytes 
3a6d845
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4397333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0866/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": 0.0002803729487402998,
      "loss": 3.3184,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.25733333333333336,
      "eval_loss": 2.8400001525878906,
      "eval_runtime": 13.4165,
      "eval_samples_per_second": 279.506,
      "eval_steps_per_second": 4.398,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.539268493652344,
      "learning_rate": 0.00022581553795296964,
      "loss": 2.7138,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3045333333333333,
      "eval_loss": 2.5628294944763184,
      "eval_runtime": 13.3338,
      "eval_samples_per_second": 281.24,
      "eval_steps_per_second": 4.425,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 30.986927032470703,
      "learning_rate": 0.00015094341499741014,
      "loss": 2.4396,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.34053333333333335,
      "eval_loss": 2.3752715587615967,
      "eval_runtime": 13.2597,
      "eval_samples_per_second": 282.812,
      "eval_steps_per_second": 4.45,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 35.424373626708984,
      "learning_rate": 7.58185047551672e-05,
      "loss": 2.1406,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.40613333333333335,
      "eval_loss": 2.1301815509796143,
      "eval_runtime": 13.254,
      "eval_samples_per_second": 282.932,
      "eval_steps_per_second": 4.451,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 30.954788208007812,
      "learning_rate": 2.0570466257110352e-05,
      "loss": 1.8645,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.43866666666666665,
      "eval_loss": 2.02327299118042,
      "eval_runtime": 12.6244,
      "eval_samples_per_second": 297.044,
      "eval_steps_per_second": 4.673,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 23.960506439208984,
      "learning_rate": 2.9668021975126634e-09,
      "loss": 1.6488,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4397333333333333,
      "eval_loss": 2.0386009216308594,
      "eval_runtime": 13.4349,
      "eval_samples_per_second": 279.125,
      "eval_steps_per_second": 4.392,
      "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
}