Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0949

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0949
File size: 4,338 Bytes 
e6eb23b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3429333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0949/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": 15.467879295349121,
      "learning_rate": 0.0005,
      "loss": 3.525,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.16746666666666668,
      "eval_loss": 3.1427931785583496,
      "eval_runtime": 10.3267,
      "eval_samples_per_second": 363.136,
      "eval_steps_per_second": 5.713,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.832212448120117,
      "learning_rate": 0.0005,
      "loss": 3.0335,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20293333333333333,
      "eval_loss": 3.0235369205474854,
      "eval_runtime": 10.4334,
      "eval_samples_per_second": 359.424,
      "eval_steps_per_second": 5.655,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 14.095104217529297,
      "learning_rate": 0.0005,
      "loss": 2.867,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.23226666666666668,
      "eval_loss": 2.8861515522003174,
      "eval_runtime": 10.4311,
      "eval_samples_per_second": 359.501,
      "eval_steps_per_second": 5.656,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.9379825592041,
      "learning_rate": 0.0005,
      "loss": 2.727,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.25893333333333335,
      "eval_loss": 2.753180742263794,
      "eval_runtime": 10.3294,
      "eval_samples_per_second": 363.043,
      "eval_steps_per_second": 5.712,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 14.556490898132324,
      "learning_rate": 0.0005,
      "loss": 2.5951,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2634666666666667,
      "eval_loss": 2.749525785446167,
      "eval_runtime": 10.6106,
      "eval_samples_per_second": 353.42,
      "eval_steps_per_second": 5.56,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 15.043558120727539,
      "learning_rate": 0.0005,
      "loss": 2.4938,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2968,
      "eval_loss": 2.600337505340576,
      "eval_runtime": 10.6579,
      "eval_samples_per_second": 351.853,
      "eval_steps_per_second": 5.536,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 15.658565521240234,
      "learning_rate": 0.0005,
      "loss": 2.3948,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.31066666666666665,
      "eval_loss": 2.563699722290039,
      "eval_runtime": 10.8152,
      "eval_samples_per_second": 346.733,
      "eval_steps_per_second": 5.455,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 8.630295753479004,
      "learning_rate": 0.0005,
      "loss": 2.3226,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3152,
      "eval_loss": 2.4947543144226074,
      "eval_runtime": 10.1945,
      "eval_samples_per_second": 367.844,
      "eval_steps_per_second": 5.787,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 14.360987663269043,
      "learning_rate": 0.0005,
      "loss": 2.2324,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.3429333333333333,
      "eval_loss": 2.422478675842285,
      "eval_runtime": 10.3778,
      "eval_samples_per_second": 361.349,
      "eval_steps_per_second": 5.685,
      "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
}