Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0721

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0721
File size: 3,231 Bytes 
50cc4ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4264,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0721/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": 37.503623962402344,
      "learning_rate": 0.0002506006006006006,
      "loss": 3.4132,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2056,
      "eval_loss": 2.9884862899780273,
      "eval_runtime": 11.9805,
      "eval_samples_per_second": 313.008,
      "eval_steps_per_second": 4.925,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.49224281311035,
      "learning_rate": 0.00020060060060060058,
      "loss": 2.8108,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2632,
      "eval_loss": 2.753221273422241,
      "eval_runtime": 11.6883,
      "eval_samples_per_second": 320.833,
      "eval_steps_per_second": 5.048,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 29.525482177734375,
      "learning_rate": 0.00015060060060060059,
      "loss": 2.5578,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3192,
      "eval_loss": 2.5137317180633545,
      "eval_runtime": 11.8321,
      "eval_samples_per_second": 316.934,
      "eval_steps_per_second": 4.986,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 44.18714904785156,
      "learning_rate": 0.00010060060060060059,
      "loss": 2.3043,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.35786666666666667,
      "eval_loss": 2.344916820526123,
      "eval_runtime": 12.2024,
      "eval_samples_per_second": 307.317,
      "eval_steps_per_second": 4.835,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 53.262699127197266,
      "learning_rate": 5.0600600600600595e-05,
      "loss": 2.0625,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3930666666666667,
      "eval_loss": 2.194922924041748,
      "eval_runtime": 13.0784,
      "eval_samples_per_second": 286.732,
      "eval_steps_per_second": 4.511,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 19.675737380981445,
      "learning_rate": 6.006006006006005e-07,
      "loss": 1.7925,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4264,
      "eval_loss": 2.1091229915618896,
      "eval_runtime": 11.739,
      "eval_samples_per_second": 319.448,
      "eval_steps_per_second": 5.026,
      "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
}