Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0876

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0876
File size: 4,482 Bytes 
7500ac0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.44426666666666664,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0876/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": 23.972213745117188,
      "learning_rate": 0.0002911145304096916,
      "loss": 3.4281,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19386666666666666,
      "eval_loss": 3.0675785541534424,
      "eval_runtime": 11.8405,
      "eval_samples_per_second": 316.71,
      "eval_steps_per_second": 4.983,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.179256439208984,
      "learning_rate": 0.00026520930752569493,
      "loss": 2.8746,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2504,
      "eval_loss": 2.7793874740600586,
      "eval_runtime": 11.6501,
      "eval_samples_per_second": 321.885,
      "eval_steps_per_second": 5.064,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.54439353942871,
      "learning_rate": 0.00022540814184580826,
      "loss": 2.6108,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.29706666666666665,
      "eval_loss": 2.579789638519287,
      "eval_runtime": 12.497,
      "eval_samples_per_second": 300.072,
      "eval_steps_per_second": 4.721,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 41.20870590209961,
      "learning_rate": 0.00017651164135367125,
      "loss": 2.3736,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.34346666666666664,
      "eval_loss": 2.4240145683288574,
      "eval_runtime": 12.2817,
      "eval_samples_per_second": 305.333,
      "eval_steps_per_second": 4.804,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 27.161012649536133,
      "learning_rate": 0.00012441744564412654,
      "loss": 2.1733,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3808,
      "eval_loss": 2.265169858932495,
      "eval_runtime": 12.2361,
      "eval_samples_per_second": 306.471,
      "eval_steps_per_second": 4.822,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 25.194133758544922,
      "learning_rate": 7.540888354819138e-05,
      "loss": 1.9376,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.42506666666666665,
      "eval_loss": 2.1541152000427246,
      "eval_runtime": 11.7925,
      "eval_samples_per_second": 317.998,
      "eval_steps_per_second": 5.003,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 36.622493743896484,
      "learning_rate": 3.5397110943979596e-05,
      "loss": 1.6978,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4298666666666667,
      "eval_loss": 2.110281229019165,
      "eval_runtime": 11.803,
      "eval_samples_per_second": 317.717,
      "eval_steps_per_second": 4.999,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 20.56290626525879,
      "learning_rate": 9.20813811843163e-06,
      "loss": 1.4752,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.44053333333333333,
      "eval_loss": 2.151519298553467,
      "eval_runtime": 11.7022,
      "eval_samples_per_second": 320.453,
      "eval_steps_per_second": 5.042,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 39.504180908203125,
      "learning_rate": 7.417023831113311e-10,
      "loss": 1.3405,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.44426666666666664,
      "eval_loss": 2.1652350425720215,
      "eval_runtime": 16.3212,
      "eval_samples_per_second": 229.762,
      "eval_steps_per_second": 3.615,
      "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
}