Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0019

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0019
File size: 4,263 Bytes 
653615e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.45093333333333335,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0019/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": 0.0003,
      "loss": 3.1754,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2624,
      "eval_loss": 2.7426342964172363,
      "eval_runtime": 6.8614,
      "eval_samples_per_second": 546.538,
      "eval_steps_per_second": 8.599,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.31804084777832,
      "learning_rate": 0.0003,
      "loss": 2.625,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3032,
      "eval_loss": 2.519196033477783,
      "eval_runtime": 6.9127,
      "eval_samples_per_second": 542.48,
      "eval_steps_per_second": 8.535,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 27.870952606201172,
      "learning_rate": 0.0003,
      "loss": 2.3848,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.35013333333333335,
      "eval_loss": 2.3492226600646973,
      "eval_runtime": 6.9277,
      "eval_samples_per_second": 541.308,
      "eval_steps_per_second": 8.517,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.502286911010742,
      "learning_rate": 0.0003,
      "loss": 2.1988,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.36106666666666665,
      "eval_loss": 2.288694381713867,
      "eval_runtime": 6.8525,
      "eval_samples_per_second": 547.245,
      "eval_steps_per_second": 8.61,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 29.290599822998047,
      "learning_rate": 0.0003,
      "loss": 2.0516,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3824,
      "eval_loss": 2.2070343494415283,
      "eval_runtime": 6.9718,
      "eval_samples_per_second": 537.878,
      "eval_steps_per_second": 8.463,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 15.634681701660156,
      "learning_rate": 0.0003,
      "loss": 1.8885,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4056,
      "eval_loss": 2.106214761734009,
      "eval_runtime": 6.8134,
      "eval_samples_per_second": 550.384,
      "eval_steps_per_second": 8.659,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 14.558621406555176,
      "learning_rate": 0.0003,
      "loss": 1.7686,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4272,
      "eval_loss": 2.0044667720794678,
      "eval_runtime": 7.069,
      "eval_samples_per_second": 530.487,
      "eval_steps_per_second": 8.346,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 1.6371,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4448,
      "eval_loss": 2.054042339324951,
      "eval_runtime": 7.423,
      "eval_samples_per_second": 505.188,
      "eval_steps_per_second": 7.948,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 17.276193618774414,
      "learning_rate": 0.0003,
      "loss": 1.5217,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.45093333333333335,
      "eval_loss": 1.9228202104568481,
      "eval_runtime": 6.8309,
      "eval_samples_per_second": 548.977,
      "eval_steps_per_second": 8.637,
      "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
}