Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0115

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0115
File size: 4,437 Bytes 
8a2337a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4176,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0115/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": 16.193632125854492,
      "learning_rate": 0.00044477811144477816,
      "loss": 3.4567,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17466666666666666,
      "eval_loss": 3.1399567127227783,
      "eval_runtime": 7.2408,
      "eval_samples_per_second": 517.897,
      "eval_steps_per_second": 8.148,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 29.858867645263672,
      "learning_rate": 0.00038922255588922256,
      "loss": 2.961,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.23786666666666667,
      "eval_loss": 2.823578119277954,
      "eval_runtime": 7.2152,
      "eval_samples_per_second": 519.738,
      "eval_steps_per_second": 8.177,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.40850257873535,
      "learning_rate": 0.00033366700033366696,
      "loss": 2.7576,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.26666666666666666,
      "eval_loss": 2.7216010093688965,
      "eval_runtime": 7.1069,
      "eval_samples_per_second": 527.66,
      "eval_steps_per_second": 8.302,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 17.330432891845703,
      "learning_rate": 0.00027811144477811147,
      "loss": 2.5944,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2968,
      "eval_loss": 2.60909104347229,
      "eval_runtime": 7.1012,
      "eval_samples_per_second": 528.077,
      "eval_steps_per_second": 8.308,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.445401191711426,
      "learning_rate": 0.0002225558892225559,
      "loss": 2.4144,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.32666666666666666,
      "eval_loss": 2.479083299636841,
      "eval_runtime": 7.7725,
      "eval_samples_per_second": 482.471,
      "eval_steps_per_second": 7.591,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 17.249067306518555,
      "learning_rate": 0.00016700033366700035,
      "loss": 2.2316,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.36133333333333334,
      "eval_loss": 2.3110103607177734,
      "eval_runtime": 7.1573,
      "eval_samples_per_second": 523.94,
      "eval_steps_per_second": 8.243,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00011161161161161162,
      "loss": 2.0531,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.37866666666666665,
      "eval_loss": 2.247860908508301,
      "eval_runtime": 7.1253,
      "eval_samples_per_second": 526.296,
      "eval_steps_per_second": 8.28,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 33.24580383300781,
      "learning_rate": 5.605605605605606e-05,
      "loss": 1.8771,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4128,
      "eval_loss": 2.202280282974243,
      "eval_runtime": 7.4642,
      "eval_samples_per_second": 502.395,
      "eval_steps_per_second": 7.904,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 26.370620727539062,
      "learning_rate": 5.005005005005005e-07,
      "loss": 1.6849,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.4176,
      "eval_loss": 2.150923490524292,
      "eval_runtime": 7.6644,
      "eval_samples_per_second": 489.278,
      "eval_steps_per_second": 7.698,
      "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
}