Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0860

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0860
File size: 3,280 Bytes 
5d80b80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9234666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0860/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": 45.48875427246094,
      "learning_rate": 8.343343343343344e-05,
      "loss": 0.9773,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8464,
      "eval_loss": 0.5149207711219788,
      "eval_runtime": 11.234,
      "eval_samples_per_second": 333.809,
      "eval_steps_per_second": 5.252,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 99.65483093261719,
      "learning_rate": 6.676676676676677e-05,
      "loss": 0.3397,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8506666666666667,
      "eval_loss": 0.5220389366149902,
      "eval_runtime": 11.2915,
      "eval_samples_per_second": 332.108,
      "eval_steps_per_second": 5.225,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.13939429819583893,
      "learning_rate": 5.01001001001001e-05,
      "loss": 0.159,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.4223076105117798,
      "eval_runtime": 11.3858,
      "eval_samples_per_second": 329.357,
      "eval_steps_per_second": 5.182,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 28.183198928833008,
      "learning_rate": 3.3433433433433435e-05,
      "loss": 0.0743,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8994666666666666,
      "eval_loss": 0.37113964557647705,
      "eval_runtime": 11.21,
      "eval_samples_per_second": 334.523,
      "eval_steps_per_second": 5.263,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.007132452912628651,
      "learning_rate": 1.6766766766766767e-05,
      "loss": 0.0271,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9114666666666666,
      "eval_loss": 0.3459804952144623,
      "eval_runtime": 11.2243,
      "eval_samples_per_second": 334.097,
      "eval_steps_per_second": 5.256,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.5734689235687256,
      "learning_rate": 1.001001001001001e-07,
      "loss": 0.0058,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9234666666666667,
      "eval_loss": 0.31814101338386536,
      "eval_runtime": 11.1505,
      "eval_samples_per_second": 336.307,
      "eval_steps_per_second": 5.291,
      "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
}