Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0666

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0666
File size: 2,829 Bytes 
e4e51b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.41786666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0666/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": 20.00240707397461,
      "learning_rate": 0.00027184967850358286,
      "loss": 3.3199,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2136,
      "eval_loss": 2.9132463932037354,
      "eval_runtime": 11.1538,
      "eval_samples_per_second": 336.208,
      "eval_steps_per_second": 5.29,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.460432052612305,
      "learning_rate": 0.00019715932444832964,
      "loss": 2.7265,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2624,
      "eval_loss": 2.7010984420776367,
      "eval_runtime": 11.9713,
      "eval_samples_per_second": 313.249,
      "eval_steps_per_second": 4.928,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 30.304563522338867,
      "learning_rate": 0.00010445571134029838,
      "loss": 2.4083,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3584,
      "eval_loss": 2.3414859771728516,
      "eval_runtime": 11.1083,
      "eval_samples_per_second": 337.584,
      "eval_steps_per_second": 5.311,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 2.931633569361981e-05,
      "loss": 2.0859,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.408,
      "eval_loss": 2.1611359119415283,
      "eval_runtime": 11.1904,
      "eval_samples_per_second": 335.11,
      "eval_steps_per_second": 5.272,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 38.265342712402344,
      "learning_rate": 4.272188967840984e-09,
      "loss": 1.8348,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.41786666666666666,
      "eval_loss": 2.126314640045166,
      "eval_runtime": 11.7395,
      "eval_samples_per_second": 319.433,
      "eval_steps_per_second": 5.026,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}