Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0735

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0735
File size: 3,248 Bytes 
49003be
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.92,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0735/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": 4.661762714385986,
      "learning_rate": 6.657472928225117e-05,
      "loss": 0.7301,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8589333333333333,
      "eval_loss": 0.482107937335968,
      "eval_runtime": 13.4349,
      "eval_samples_per_second": 279.124,
      "eval_steps_per_second": 4.392,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.31866455078125,
      "learning_rate": 5.689582334051816e-05,
      "loss": 0.2431,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8589333333333333,
      "eval_loss": 0.47696444392204285,
      "eval_runtime": 13.0795,
      "eval_samples_per_second": 286.709,
      "eval_steps_per_second": 4.511,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.42184796929359436,
      "learning_rate": 4.288018105154487e-05,
      "loss": 0.1063,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.40894466638565063,
      "eval_runtime": 12.1442,
      "eval_samples_per_second": 308.788,
      "eval_steps_per_second": 4.858,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.004256879910826683,
      "learning_rate": 2.7303772261234784e-05,
      "loss": 0.0483,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9008,
      "eval_loss": 0.3822232782840729,
      "eval_runtime": 12.1331,
      "eval_samples_per_second": 309.073,
      "eval_steps_per_second": 4.863,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.008288528770208359,
      "learning_rate": 1.325169576262615e-05,
      "loss": 0.0112,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9088,
      "eval_loss": 0.40360990166664124,
      "eval_runtime": 11.9958,
      "eval_samples_per_second": 312.608,
      "eval_steps_per_second": 4.918,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.7116589546203613,
      "learning_rate": 3.5071376436769933e-06,
      "loss": 0.0016,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.92,
      "eval_loss": 0.36637216806411743,
      "eval_runtime": 12.2073,
      "eval_samples_per_second": 307.194,
      "eval_steps_per_second": 4.833,
      "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
}