Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0756

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0756
File size: 4,483 Bytes 
21f8a18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9365333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0756/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": 19.1375675201416,
      "learning_rate": 8.006006006006006e-05,
      "loss": 0.7685,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8752,
      "eval_loss": 0.41211843490600586,
      "eval_runtime": 11.9969,
      "eval_samples_per_second": 312.581,
      "eval_steps_per_second": 4.918,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 45.84107208251953,
      "learning_rate": 7.006006006006006e-05,
      "loss": 0.2391,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8861333333333333,
      "eval_loss": 0.413800448179245,
      "eval_runtime": 12.1081,
      "eval_samples_per_second": 309.709,
      "eval_steps_per_second": 4.873,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.77489709854126,
      "learning_rate": 6.006006006006006e-05,
      "loss": 0.1214,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8986666666666666,
      "eval_loss": 0.38332024216651917,
      "eval_runtime": 10.9775,
      "eval_samples_per_second": 341.608,
      "eval_steps_per_second": 5.375,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.00907878577709198,
      "learning_rate": 5.0060060060060066e-05,
      "loss": 0.0688,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9032,
      "eval_loss": 0.36377084255218506,
      "eval_runtime": 12.3647,
      "eval_samples_per_second": 303.283,
      "eval_steps_per_second": 4.772,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0002547889016568661,
      "learning_rate": 4.006006006006007e-05,
      "loss": 0.038,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9085333333333333,
      "eval_loss": 0.4099878966808319,
      "eval_runtime": 12.4053,
      "eval_samples_per_second": 302.291,
      "eval_steps_per_second": 4.756,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5097998380661011,
      "learning_rate": 3.0060060060060065e-05,
      "loss": 0.0145,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9170666666666667,
      "eval_loss": 0.3534680902957916,
      "eval_runtime": 12.4811,
      "eval_samples_per_second": 300.453,
      "eval_steps_per_second": 4.727,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.00016609852900728583,
      "learning_rate": 2.0060060060060062e-05,
      "loss": 0.0033,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9288,
      "eval_loss": 0.3495325744152069,
      "eval_runtime": 11.9931,
      "eval_samples_per_second": 312.681,
      "eval_steps_per_second": 4.92,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0003556159499567002,
      "learning_rate": 1.0060060060060061e-05,
      "loss": 0.0005,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9362666666666667,
      "eval_loss": 0.31445884704589844,
      "eval_runtime": 11.8888,
      "eval_samples_per_second": 315.424,
      "eval_steps_per_second": 4.963,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.0025154200848191977,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.0003,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9365333333333333,
      "eval_loss": 0.3113086521625519,
      "eval_runtime": 12.2131,
      "eval_samples_per_second": 307.047,
      "eval_steps_per_second": 4.831,
      "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
}