Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0022

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0022
File size: 3,660 Bytes 
81afd0b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.43306666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0022/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 0.0002576576576576576,
      "loss": 3.331,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22533333333333333,
      "eval_loss": 2.916614055633545,
      "eval_runtime": 6.043,
      "eval_samples_per_second": 620.556,
      "eval_steps_per_second": 9.763,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.480674743652344,
      "learning_rate": 0.0002148005148005148,
      "loss": 2.764,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2733333333333333,
      "eval_loss": 2.743821382522583,
      "eval_runtime": 6.4239,
      "eval_samples_per_second": 583.757,
      "eval_steps_per_second": 9.184,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 22.37212562561035,
      "learning_rate": 0.0001719433719433719,
      "loss": 2.4879,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3192,
      "eval_loss": 2.4924168586730957,
      "eval_runtime": 6.049,
      "eval_samples_per_second": 619.937,
      "eval_steps_per_second": 9.754,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 20.755020141601562,
      "learning_rate": 0.00012908622908622906,
      "loss": 2.2465,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3586666666666667,
      "eval_loss": 2.3621773719787598,
      "eval_runtime": 6.0494,
      "eval_samples_per_second": 619.897,
      "eval_steps_per_second": 9.753,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 31.968097686767578,
      "learning_rate": 8.622908622908623e-05,
      "loss": 1.9752,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4029333333333333,
      "eval_loss": 2.2212438583374023,
      "eval_runtime": 6.0782,
      "eval_samples_per_second": 616.961,
      "eval_steps_per_second": 9.707,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.712707042694092,
      "learning_rate": 4.337194337194337e-05,
      "loss": 1.635,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4202666666666667,
      "eval_loss": 2.181201934814453,
      "eval_runtime": 6.6146,
      "eval_samples_per_second": 566.924,
      "eval_steps_per_second": 8.92,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 45.38018035888672,
      "learning_rate": 5.148005148005147e-07,
      "loss": 1.2094,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.43306666666666666,
      "eval_loss": 2.3172547817230225,
      "eval_runtime": 6.1674,
      "eval_samples_per_second": 608.033,
      "eval_steps_per_second": 9.566,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}