Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0741

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0741
File size: 4,454 Bytes 
eb3ea6e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9368,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0741/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": 2.9106113962682575e-05,
      "loss": 0.8153,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8885333333333333,
      "eval_loss": 0.3795890510082245,
      "eval_runtime": 12.5861,
      "eval_samples_per_second": 297.948,
      "eval_steps_per_second": 4.688,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.16534423828125,
      "learning_rate": 2.6510855361961218e-05,
      "loss": 0.2056,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9066666666666666,
      "eval_loss": 0.3051028549671173,
      "eval_runtime": 11.5167,
      "eval_samples_per_second": 325.615,
      "eval_steps_per_second": 5.123,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6197761297225952,
      "learning_rate": 2.2527217722455156e-05,
      "loss": 0.0934,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9146666666666666,
      "eval_loss": 0.306363582611084,
      "eval_runtime": 11.6528,
      "eval_samples_per_second": 321.811,
      "eval_steps_per_second": 5.063,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.234869956970215,
      "learning_rate": 1.763568653571882e-05,
      "loss": 0.0482,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9144,
      "eval_loss": 0.3161237835884094,
      "eval_runtime": 11.538,
      "eval_samples_per_second": 325.014,
      "eval_steps_per_second": 5.114,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3970872759819031,
      "learning_rate": 1.2426252654184347e-05,
      "loss": 0.0193,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9194666666666667,
      "eval_loss": 0.3259260058403015,
      "eval_runtime": 11.502,
      "eval_samples_per_second": 326.031,
      "eval_steps_per_second": 5.13,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.017822621390223503,
      "learning_rate": 7.5272506870206094e-06,
      "loss": 0.0072,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9341333333333334,
      "eval_loss": 0.286670446395874,
      "eval_runtime": 12.3994,
      "eval_samples_per_second": 302.435,
      "eval_steps_per_second": 4.758,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0018657544860616326,
      "learning_rate": 3.5295725730362483e-06,
      "loss": 0.0022,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9330666666666667,
      "eval_loss": 0.28996291756629944,
      "eval_runtime": 11.4697,
      "eval_samples_per_second": 326.949,
      "eval_steps_per_second": 5.144,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.006840866524726152,
      "learning_rate": 9.153972922231291e-07,
      "loss": 0.0013,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.936,
      "eval_loss": 0.2823556661605835,
      "eval_runtime": 11.6638,
      "eval_samples_per_second": 321.507,
      "eval_steps_per_second": 5.058,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.2528367042541504,
      "learning_rate": 3.2964565453985627e-11,
      "loss": 0.0006,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.2811087965965271,
      "eval_runtime": 12.3664,
      "eval_samples_per_second": 303.24,
      "eval_steps_per_second": 4.771,
      "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
}