Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0488

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0488
File size: 2,847 Bytes 
0695e50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.33573333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0488/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 19.07137107849121,
      "learning_rate": 0.0004670935782735732,
      "loss": 3.476,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1816,
      "eval_loss": 3.115863561630249,
      "eval_runtime": 11.7162,
      "eval_samples_per_second": 320.07,
      "eval_steps_per_second": 5.036,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.870302200317383,
      "learning_rate": 0.00037601988894783115,
      "loss": 2.9947,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2184,
      "eval_loss": 2.920520305633545,
      "eval_runtime": 12.1716,
      "eval_samples_per_second": 308.093,
      "eval_steps_per_second": 4.847,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.975236892700195,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.7684,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.26026666666666665,
      "eval_loss": 2.724780797958374,
      "eval_runtime": 11.7539,
      "eval_samples_per_second": 319.044,
      "eval_steps_per_second": 5.02,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 24.22864532470703,
      "learning_rate": 0.00012602267032890265,
      "loss": 2.5552,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2896,
      "eval_loss": 2.5869839191436768,
      "eval_runtime": 11.039,
      "eval_samples_per_second": 339.705,
      "eval_steps_per_second": 5.345,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 30.69786262512207,
      "learning_rate": 3.408569387468488e-05,
      "loss": 2.3463,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.33573333333333333,
      "eval_loss": 2.451549530029297,
      "eval_runtime": 11.6252,
      "eval_samples_per_second": 322.575,
      "eval_steps_per_second": 5.075,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}