Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0097

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0097
File size: 4,471 Bytes 
a5ead3f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9274666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0097/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": 8.733435912290749e-05,
      "loss": 0.8241,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8424,
      "eval_loss": 0.5006316304206848,
      "eval_runtime": 5.7913,
      "eval_samples_per_second": 647.518,
      "eval_steps_per_second": 10.188,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.048438165336847305,
      "learning_rate": 7.956279225770849e-05,
      "loss": 0.2929,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8565333333333334,
      "eval_loss": 0.46680423617362976,
      "eval_runtime": 6.5438,
      "eval_samples_per_second": 573.059,
      "eval_steps_per_second": 9.016,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 57.208065032958984,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.1702,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.49625909328460693,
      "eval_runtime": 6.4559,
      "eval_samples_per_second": 580.865,
      "eval_steps_per_second": 9.139,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.141869068145752,
      "learning_rate": 5.295349240610138e-05,
      "loss": 0.0965,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.42235833406448364,
      "eval_runtime": 6.5667,
      "eval_samples_per_second": 571.06,
      "eval_steps_per_second": 8.985,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4017585515975952,
      "learning_rate": 3.7325233693237964e-05,
      "loss": 0.0466,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8954666666666666,
      "eval_loss": 0.41986626386642456,
      "eval_runtime": 5.8293,
      "eval_samples_per_second": 643.306,
      "eval_steps_per_second": 10.121,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07465048879384995,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.0151,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.912,
      "eval_loss": 0.39512571692466736,
      "eval_runtime": 5.7113,
      "eval_samples_per_second": 656.596,
      "eval_steps_per_second": 10.33,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.00887842196971178,
      "learning_rate": 1.061913328319388e-05,
      "loss": 0.0029,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9258666666666666,
      "eval_loss": 0.32653334736824036,
      "eval_runtime": 6.1402,
      "eval_samples_per_second": 610.73,
      "eval_steps_per_second": 9.609,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0004780263698194176,
      "learning_rate": 2.7624414355294893e-06,
      "loss": 0.0014,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9264,
      "eval_loss": 0.3222518563270569,
      "eval_runtime": 5.6469,
      "eval_samples_per_second": 664.077,
      "eval_steps_per_second": 10.448,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.00014915411884430796,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0005,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9274666666666667,
      "eval_loss": 0.32382291555404663,
      "eval_runtime": 5.7666,
      "eval_samples_per_second": 650.298,
      "eval_steps_per_second": 10.231,
      "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
}