Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0263

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0263
File size: 3,676 Bytes 
6054d57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4962666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0263/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": 23.716232299804688,
      "learning_rate": 0.0002575289575289575,
      "loss": 3.1413,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.24133333333333334,
      "eval_loss": 2.7876899242401123,
      "eval_runtime": 10.7227,
      "eval_samples_per_second": 349.724,
      "eval_steps_per_second": 5.502,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.611970901489258,
      "learning_rate": 0.00021467181467181467,
      "loss": 2.4842,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3328,
      "eval_loss": 2.427351713180542,
      "eval_runtime": 11.133,
      "eval_samples_per_second": 336.837,
      "eval_steps_per_second": 5.3,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 26.599605560302734,
      "learning_rate": 0.0001718146718146718,
      "loss": 2.1871,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.36666666666666664,
      "eval_loss": 2.254958391189575,
      "eval_runtime": 10.4128,
      "eval_samples_per_second": 360.135,
      "eval_steps_per_second": 5.666,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.49584197998047,
      "learning_rate": 0.00012895752895752895,
      "loss": 1.916,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.41706666666666664,
      "eval_loss": 2.062950849533081,
      "eval_runtime": 10.372,
      "eval_samples_per_second": 361.55,
      "eval_steps_per_second": 5.688,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.879638671875,
      "learning_rate": 8.61003861003861e-05,
      "loss": 1.6534,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.45626666666666665,
      "eval_loss": 1.9382479190826416,
      "eval_runtime": 10.6068,
      "eval_samples_per_second": 353.546,
      "eval_steps_per_second": 5.562,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 85.64336395263672,
      "learning_rate": 4.324324324324324e-05,
      "loss": 1.3429,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4770666666666667,
      "eval_loss": 1.8900713920593262,
      "eval_runtime": 10.7516,
      "eval_samples_per_second": 348.786,
      "eval_steps_per_second": 5.488,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 30.614139556884766,
      "learning_rate": 3.861003861003861e-07,
      "loss": 0.9779,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4962666666666667,
      "eval_loss": 1.9947816133499146,
      "eval_runtime": 11.2513,
      "eval_samples_per_second": 333.295,
      "eval_steps_per_second": 5.244,
      "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
}