Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0636

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0636
File size: 4,313 Bytes 
d495a07
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.34026666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0636/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 25.15431022644043,
      "learning_rate": 0.0005,
      "loss": 3.4452,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17466666666666666,
      "eval_loss": 3.132124423980713,
      "eval_runtime": 13.4229,
      "eval_samples_per_second": 279.373,
      "eval_steps_per_second": 4.395,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.65234375,
      "learning_rate": 0.0005,
      "loss": 2.9675,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.22426666666666667,
      "eval_loss": 2.913943290710449,
      "eval_runtime": 12.4633,
      "eval_samples_per_second": 300.883,
      "eval_steps_per_second": 4.734,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 21.702959060668945,
      "learning_rate": 0.0005,
      "loss": 2.8415,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.23066666666666666,
      "eval_loss": 2.8593287467956543,
      "eval_runtime": 12.426,
      "eval_samples_per_second": 301.785,
      "eval_steps_per_second": 4.748,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.083477020263672,
      "learning_rate": 0.0005,
      "loss": 2.7455,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.27653333333333335,
      "eval_loss": 2.6849989891052246,
      "eval_runtime": 12.2484,
      "eval_samples_per_second": 306.164,
      "eval_steps_per_second": 4.817,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.421483993530273,
      "learning_rate": 0.0005,
      "loss": 2.6459,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2848,
      "eval_loss": 2.6264588832855225,
      "eval_runtime": 11.4717,
      "eval_samples_per_second": 326.891,
      "eval_steps_per_second": 5.143,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 27.10919189453125,
      "learning_rate": 0.0005,
      "loss": 2.5473,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3072,
      "eval_loss": 2.569124460220337,
      "eval_runtime": 11.3468,
      "eval_samples_per_second": 330.489,
      "eval_steps_per_second": 5.2,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 16.007593154907227,
      "learning_rate": 0.0005,
      "loss": 2.4564,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3138666666666667,
      "eval_loss": 2.5231592655181885,
      "eval_runtime": 11.3042,
      "eval_samples_per_second": 331.736,
      "eval_steps_per_second": 5.219,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.3686,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3184,
      "eval_loss": 2.506213903427124,
      "eval_runtime": 11.3724,
      "eval_samples_per_second": 329.747,
      "eval_steps_per_second": 5.188,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 8.122834205627441,
      "learning_rate": 0.0005,
      "loss": 2.2757,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.34026666666666666,
      "eval_loss": 2.4242594242095947,
      "eval_runtime": 11.6295,
      "eval_samples_per_second": 322.455,
      "eval_steps_per_second": 5.073,
      "step": 2997
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}