Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0108

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0108
File size: 4,476 Bytes 
90bba36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9344,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0108/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": 1.9157744646072388,
      "learning_rate": 4.850126564054637e-05,
      "loss": 0.7427,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.39399003982543945,
      "eval_runtime": 4.0751,
      "eval_samples_per_second": 920.212,
      "eval_steps_per_second": 14.478,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.027789583429694176,
      "learning_rate": 4.416794553834106e-05,
      "loss": 0.213,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.33196935057640076,
      "eval_runtime": 4.0549,
      "eval_samples_per_second": 924.806,
      "eval_steps_per_second": 14.55,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3.7545362870758595e-05,
      "loss": 0.1029,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.35182154178619385,
      "eval_runtime": 4.1966,
      "eval_samples_per_second": 893.586,
      "eval_steps_per_second": 14.059,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.018823252990841866,
      "learning_rate": 2.9392810892864702e-05,
      "loss": 0.0443,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9106666666666666,
      "eval_loss": 0.33442744612693787,
      "eval_runtime": 4.1719,
      "eval_samples_per_second": 898.88,
      "eval_steps_per_second": 14.142,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2509842813014984,
      "learning_rate": 2.0710421090307246e-05,
      "loss": 0.0231,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9213333333333333,
      "eval_loss": 0.31589528918266296,
      "eval_runtime": 4.0719,
      "eval_samples_per_second": 920.948,
      "eval_steps_per_second": 14.49,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00012362049892544746,
      "learning_rate": 1.2545417811701016e-05,
      "loss": 0.0055,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9296,
      "eval_loss": 0.3054322302341461,
      "eval_runtime": 4.4158,
      "eval_samples_per_second": 849.224,
      "eval_steps_per_second": 13.361,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.09116710722446442,
      "learning_rate": 5.882620955060414e-06,
      "loss": 0.0005,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9341333333333334,
      "eval_loss": 0.2975241243839264,
      "eval_runtime": 4.0686,
      "eval_samples_per_second": 921.695,
      "eval_steps_per_second": 14.501,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0016982945380732417,
      "learning_rate": 1.5256621537052152e-06,
      "loss": 0.0001,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9330666666666667,
      "eval_loss": 0.295346736907959,
      "eval_runtime": 4.0577,
      "eval_samples_per_second": 924.174,
      "eval_steps_per_second": 14.54,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.00819256529211998,
      "learning_rate": 5.494094242330938e-11,
      "loss": 0.0001,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9344,
      "eval_loss": 0.2916950583457947,
      "eval_runtime": 4.1225,
      "eval_samples_per_second": 909.648,
      "eval_steps_per_second": 14.312,
      "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
}