Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0978

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0978
File size: 3,273 Bytes 
6ae7dff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9293333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0978/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": Infinity,
      "learning_rate": 4.7567894803118645e-05,
      "loss": 0.7056,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8698666666666667,
      "eval_loss": 0.41644415259361267,
      "eval_runtime": 10.1074,
      "eval_samples_per_second": 371.016,
      "eval_steps_per_second": 5.837,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.755453586578369,
      "learning_rate": 4.066614560987835e-05,
      "loss": 0.1837,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.892,
      "eval_loss": 0.34696945548057556,
      "eval_runtime": 10.0908,
      "eval_samples_per_second": 371.626,
      "eval_steps_per_second": 5.847,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.023200640454888344,
      "learning_rate": 3.066152414593445e-05,
      "loss": 0.0764,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8973333333333333,
      "eval_loss": 0.3606955409049988,
      "eval_runtime": 10.0994,
      "eval_samples_per_second": 371.31,
      "eval_steps_per_second": 5.842,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.992969036102295,
      "learning_rate": 1.95355683908512e-05,
      "loss": 0.0358,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9093333333333333,
      "eval_loss": 0.3267403542995453,
      "eval_runtime": 10.271,
      "eval_samples_per_second": 365.105,
      "eval_steps_per_second": 5.744,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.003809078596532345,
      "learning_rate": 9.491910332815573e-06,
      "loss": 0.0066,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9229333333333334,
      "eval_loss": 0.3067948520183563,
      "eval_runtime": 10.183,
      "eval_samples_per_second": 368.26,
      "eval_steps_per_second": 5.794,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.021300574764609337,
      "learning_rate": 2.5198196276040782e-06,
      "loss": 0.0012,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9293333333333333,
      "eval_loss": 0.2953920066356659,
      "eval_runtime": 10.6992,
      "eval_samples_per_second": 350.495,
      "eval_steps_per_second": 5.514,
      "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
}