Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0524

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0524
File size: 3,286 Bytes 
aed8ff9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9394666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0524/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": 1.5573995113372803,
      "learning_rate": 2.572715572715573e-05,
      "loss": 0.8094,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.35094690322875977,
      "eval_runtime": 6.8816,
      "eval_samples_per_second": 544.933,
      "eval_steps_per_second": 8.574,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0041722459718585014,
      "learning_rate": 2.1441441441441442e-05,
      "loss": 0.1698,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.28002825379371643,
      "eval_runtime": 7.4039,
      "eval_samples_per_second": 506.491,
      "eval_steps_per_second": 7.969,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 32.07955551147461,
      "learning_rate": 1.715572715572716e-05,
      "loss": 0.0688,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9248,
      "eval_loss": 0.24454577267169952,
      "eval_runtime": 6.8961,
      "eval_samples_per_second": 543.783,
      "eval_steps_per_second": 8.556,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.04640292748808861,
      "learning_rate": 1.287001287001287e-05,
      "loss": 0.0268,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9357333333333333,
      "eval_loss": 0.24210183322429657,
      "eval_runtime": 6.8346,
      "eval_samples_per_second": 548.682,
      "eval_steps_per_second": 8.633,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16097280383110046,
      "learning_rate": 8.584298584298585e-06,
      "loss": 0.01,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9362666666666667,
      "eval_loss": 0.25270792841911316,
      "eval_runtime": 6.3201,
      "eval_samples_per_second": 593.343,
      "eval_steps_per_second": 9.335,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0025844352785497904,
      "learning_rate": 4.298584298584299e-06,
      "loss": 0.0031,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9394666666666667,
      "eval_loss": 0.23905640840530396,
      "eval_runtime": 6.3372,
      "eval_samples_per_second": 591.742,
      "eval_steps_per_second": 9.31,
      "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
}