Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0316

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0316
File size: 4,454 Bytes 
1ef00a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9104,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0316/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": 8.895562228895563e-05,
      "loss": 0.9096,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8234666666666667,
      "eval_loss": 0.5792152881622314,
      "eval_runtime": 12.4489,
      "eval_samples_per_second": 301.23,
      "eval_steps_per_second": 4.739,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.298056602478027,
      "learning_rate": 7.784451117784451e-05,
      "loss": 0.3305,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.48345640301704407,
      "eval_runtime": 12.4583,
      "eval_samples_per_second": 301.004,
      "eval_steps_per_second": 4.736,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.76416778564453,
      "learning_rate": 6.67334000667334e-05,
      "loss": 0.1792,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8576,
      "eval_loss": 0.5078938007354736,
      "eval_runtime": 12.0079,
      "eval_samples_per_second": 312.294,
      "eval_steps_per_second": 4.913,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0036155444104224443,
      "learning_rate": 5.562228895562229e-05,
      "loss": 0.1062,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.4855312407016754,
      "eval_runtime": 12.2484,
      "eval_samples_per_second": 306.163,
      "eval_steps_per_second": 4.817,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 149.50289916992188,
      "learning_rate": 4.451117784451118e-05,
      "loss": 0.0621,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8826666666666667,
      "eval_loss": 0.47164973616600037,
      "eval_runtime": 12.1954,
      "eval_samples_per_second": 307.493,
      "eval_steps_per_second": 4.838,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.5681352615356445,
      "learning_rate": 3.340006673340007e-05,
      "loss": 0.0331,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.5122829675674438,
      "eval_runtime": 12.1833,
      "eval_samples_per_second": 307.798,
      "eval_steps_per_second": 4.843,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.14721190929412842,
      "learning_rate": 2.2288955622288957e-05,
      "loss": 0.0119,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9021333333333333,
      "eval_loss": 0.42940565943717957,
      "eval_runtime": 12.3423,
      "eval_samples_per_second": 303.834,
      "eval_steps_per_second": 4.78,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.16703183948993683,
      "learning_rate": 1.1177844511177845e-05,
      "loss": 0.0042,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9069333333333334,
      "eval_loss": 0.40795499086380005,
      "eval_runtime": 11.7558,
      "eval_samples_per_second": 318.99,
      "eval_steps_per_second": 5.019,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.0007953958120197058,
      "learning_rate": 6.673340006673341e-08,
      "loss": 0.0014,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9104,
      "eval_loss": 0.3699820935726166,
      "eval_runtime": 12.0861,
      "eval_samples_per_second": 310.275,
      "eval_steps_per_second": 4.882,
      "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
}