Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0753

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0753
File size: 4,057 Bytes 
e1b6cb0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.4168,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0753/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 0.00048141860138016556,
      "loss": 3.4413,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18773333333333334,
      "eval_loss": 3.0695786476135254,
      "eval_runtime": 12.7673,
      "eval_samples_per_second": 293.719,
      "eval_steps_per_second": 4.621,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 29.53740692138672,
      "learning_rate": 0.00042760859989611786,
      "loss": 2.9489,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.22346666666666667,
      "eval_loss": 2.870962381362915,
      "eval_runtime": 12.9055,
      "eval_samples_per_second": 290.573,
      "eval_steps_per_second": 4.572,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.671371459960938,
      "learning_rate": 0.00034675929910385353,
      "loss": 2.7427,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.27013333333333334,
      "eval_loss": 2.6794707775115967,
      "eval_runtime": 12.4961,
      "eval_samples_per_second": 300.094,
      "eval_steps_per_second": 4.721,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.942582130432129,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.5241,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3184,
      "eval_loss": 2.49371600151062,
      "eval_runtime": 12.4718,
      "eval_samples_per_second": 300.677,
      "eval_steps_per_second": 4.731,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 37.451560974121094,
      "learning_rate": 0.00015541971169821895,
      "loss": 2.3032,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3549333333333333,
      "eval_loss": 2.3511571884155273,
      "eval_runtime": 12.4943,
      "eval_samples_per_second": 300.137,
      "eval_steps_per_second": 4.722,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 33.6088981628418,
      "learning_rate": 7.405914276967749e-05,
      "loss": 2.0744,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.38986666666666664,
      "eval_loss": 2.196793556213379,
      "eval_runtime": 12.4538,
      "eval_samples_per_second": 301.113,
      "eval_steps_per_second": 4.738,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 20.018169403076172,
      "learning_rate": 1.9483974446610292e-05,
      "loss": 1.839,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.40853333333333336,
      "eval_loss": 2.1606106758117676,
      "eval_runtime": 11.3482,
      "eval_samples_per_second": 330.449,
      "eval_steps_per_second": 5.199,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 35.89796447753906,
      "learning_rate": 2.7813810714871766e-09,
      "loss": 1.6726,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4168,
      "eval_loss": 2.168578863143921,
      "eval_runtime": 12.4386,
      "eval_samples_per_second": 301.482,
      "eval_steps_per_second": 4.743,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}