Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0731

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0731
File size: 4,460 Bytes 
34212d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.41786666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0731/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": Infinity,
      "learning_rate": 0.00048519088401615274,
      "loss": 3.4037,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17946666666666666,
      "eval_loss": 2.9968698024749756,
      "eval_runtime": 11.7649,
      "eval_samples_per_second": 318.744,
      "eval_steps_per_second": 5.015,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.930477142333984,
      "learning_rate": 0.0004420155125428249,
      "loss": 2.9202,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.23546666666666666,
      "eval_loss": 2.850100517272949,
      "eval_runtime": 12.2373,
      "eval_samples_per_second": 306.44,
      "eval_steps_per_second": 4.821,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.595916748046875,
      "learning_rate": 0.00037568023640968044,
      "loss": 2.7491,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2784,
      "eval_loss": 2.631291151046753,
      "eval_runtime": 11.9792,
      "eval_samples_per_second": 313.043,
      "eval_steps_per_second": 4.925,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 17.99822425842285,
      "learning_rate": 0.00029418606892278544,
      "loss": 2.5832,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.292,
      "eval_loss": 2.560519218444824,
      "eval_runtime": 11.9848,
      "eval_samples_per_second": 312.896,
      "eval_steps_per_second": 4.923,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 40.28602981567383,
      "learning_rate": 0.0002073624094068776,
      "loss": 2.4269,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3373333333333333,
      "eval_loss": 2.402996778488159,
      "eval_runtime": 12.2313,
      "eval_samples_per_second": 306.59,
      "eval_steps_per_second": 4.824,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 17.904094696044922,
      "learning_rate": 0.00012568147258031897,
      "loss": 2.2284,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.38293333333333335,
      "eval_loss": 2.235992431640625,
      "eval_runtime": 11.78,
      "eval_samples_per_second": 318.337,
      "eval_steps_per_second": 5.009,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 22.255460739135742,
      "learning_rate": 5.899518490663266e-05,
      "loss": 2.042,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.41173333333333334,
      "eval_loss": 2.1570637226104736,
      "eval_runtime": 11.7184,
      "eval_samples_per_second": 320.009,
      "eval_steps_per_second": 5.035,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 19.766408920288086,
      "learning_rate": 1.534689686405272e-05,
      "loss": 1.8628,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.41573333333333334,
      "eval_loss": 2.0969507694244385,
      "eval_runtime": 11.8175,
      "eval_samples_per_second": 317.326,
      "eval_steps_per_second": 4.993,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": Infinity,
      "learning_rate": 2.1976352820862743e-09,
      "loss": 1.7632,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.41786666666666666,
      "eval_loss": 2.1272125244140625,
      "eval_runtime": 11.9642,
      "eval_samples_per_second": 313.436,
      "eval_steps_per_second": 4.931,
      "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
}