Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0832

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0832
File size: 4,490 Bytes 
4a0dc5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9221333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0832/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": 15.518139839172363,
      "learning_rate": 8.731834188804772e-05,
      "loss": 0.8049,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8325333333333333,
      "eval_loss": 0.5871032476425171,
      "eval_runtime": 11.2992,
      "eval_samples_per_second": 331.883,
      "eval_steps_per_second": 5.222,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5727636218070984,
      "learning_rate": 7.953256608588366e-05,
      "loss": 0.2718,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.864,
      "eval_loss": 0.4935201108455658,
      "eval_runtime": 10.8578,
      "eval_samples_per_second": 345.375,
      "eval_steps_per_second": 5.434,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.084874629974365,
      "learning_rate": 6.758165316736547e-05,
      "loss": 0.1337,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.47873976826667786,
      "eval_runtime": 11.2724,
      "eval_samples_per_second": 332.67,
      "eval_steps_per_second": 5.234,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07774682343006134,
      "learning_rate": 5.2907059607156464e-05,
      "loss": 0.0758,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.5029803514480591,
      "eval_runtime": 10.7944,
      "eval_samples_per_second": 347.402,
      "eval_steps_per_second": 5.466,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.004232738632708788,
      "learning_rate": 3.727875796255304e-05,
      "loss": 0.034,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9034666666666666,
      "eval_loss": 0.4437032639980316,
      "eval_runtime": 10.7563,
      "eval_samples_per_second": 348.634,
      "eval_steps_per_second": 5.485,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.06607712060213089,
      "learning_rate": 2.258175206106183e-05,
      "loss": 0.009,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.42598360776901245,
      "eval_runtime": 10.7904,
      "eval_samples_per_second": 347.531,
      "eval_steps_per_second": 5.468,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03849375993013382,
      "learning_rate": 1.0588717719108745e-05,
      "loss": 0.003,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9189333333333334,
      "eval_loss": 0.3930537700653076,
      "eval_runtime": 10.8444,
      "eval_samples_per_second": 345.8,
      "eval_steps_per_second": 5.441,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0003461378801148385,
      "learning_rate": 2.7461918766693875e-06,
      "loss": 0.0007,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9213333333333333,
      "eval_loss": 0.38760945200920105,
      "eval_runtime": 11.3081,
      "eval_samples_per_second": 331.62,
      "eval_steps_per_second": 5.217,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.00037982899812050164,
      "learning_rate": 9.889369636195689e-11,
      "loss": 0.0004,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.3868175148963928,
      "eval_runtime": 11.7426,
      "eval_samples_per_second": 319.351,
      "eval_steps_per_second": 5.024,
      "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
}