Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0317

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0317
File size: 3,943 Bytes 
272bb9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3565333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0317/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": 0.0005,
      "loss": 3.3543,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20586666666666667,
      "eval_loss": 2.9818952083587646,
      "eval_runtime": 11.6475,
      "eval_samples_per_second": 321.958,
      "eval_steps_per_second": 5.065,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.080787658691406,
      "learning_rate": 0.0005,
      "loss": 2.8867,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.23893333333333333,
      "eval_loss": 2.832282066345215,
      "eval_runtime": 11.1459,
      "eval_samples_per_second": 336.447,
      "eval_steps_per_second": 5.293,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 23.232643127441406,
      "learning_rate": 0.0005,
      "loss": 2.7151,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2688,
      "eval_loss": 2.7253599166870117,
      "eval_runtime": 11.1417,
      "eval_samples_per_second": 336.572,
      "eval_steps_per_second": 5.295,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 34.21949768066406,
      "learning_rate": 0.0005,
      "loss": 2.6208,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.29893333333333333,
      "eval_loss": 2.6047494411468506,
      "eval_runtime": 11.1399,
      "eval_samples_per_second": 336.629,
      "eval_steps_per_second": 5.296,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.695234298706055,
      "learning_rate": 0.0005,
      "loss": 2.5152,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3082666666666667,
      "eval_loss": 2.5430686473846436,
      "eval_runtime": 11.8821,
      "eval_samples_per_second": 315.601,
      "eval_steps_per_second": 4.965,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 33.76705551147461,
      "learning_rate": 0.0005,
      "loss": 2.4335,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3144,
      "eval_loss": 2.464229106903076,
      "eval_runtime": 11.3344,
      "eval_samples_per_second": 330.85,
      "eval_steps_per_second": 5.205,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 29.88482093811035,
      "learning_rate": 0.0005,
      "loss": 2.3482,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.33493333333333336,
      "eval_loss": 2.419722080230713,
      "eval_runtime": 11.3849,
      "eval_samples_per_second": 329.384,
      "eval_steps_per_second": 5.182,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 18.304819107055664,
      "learning_rate": 0.0005,
      "loss": 2.254,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3565333333333333,
      "eval_loss": 2.3113932609558105,
      "eval_runtime": 11.4634,
      "eval_samples_per_second": 327.128,
      "eval_steps_per_second": 5.147,
      "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
}