Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0897

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0897
File size: 4,457 Bytes 
cbdc51b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9064,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0897/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": 6.7914265912926e-05,
      "loss": 0.8989,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8250666666666666,
      "eval_loss": 0.5874700546264648,
      "eval_runtime": 11.178,
      "eval_samples_per_second": 335.479,
      "eval_steps_per_second": 5.278,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.69859504699707,
      "learning_rate": 6.185866251124284e-05,
      "loss": 0.3314,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8616,
      "eval_loss": 0.45990410447120667,
      "eval_runtime": 11.2394,
      "eval_samples_per_second": 333.647,
      "eval_steps_per_second": 5.249,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.06787069141864777,
      "learning_rate": 5.2563508019062023e-05,
      "loss": 0.172,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8562666666666666,
      "eval_loss": 0.4968329966068268,
      "eval_runtime": 11.3151,
      "eval_samples_per_second": 331.416,
      "eval_steps_per_second": 5.214,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 30.60282325744629,
      "learning_rate": 4.1149935250010576e-05,
      "loss": 0.0976,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8778666666666667,
      "eval_loss": 0.42459017038345337,
      "eval_runtime": 11.0382,
      "eval_samples_per_second": 339.728,
      "eval_steps_per_second": 5.345,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0009135847212746739,
      "learning_rate": 2.8994589526430138e-05,
      "loss": 0.0474,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8856,
      "eval_loss": 0.44005292654037476,
      "eval_runtime": 11.0732,
      "eval_samples_per_second": 338.655,
      "eval_steps_per_second": 5.328,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00687307957559824,
      "learning_rate": 1.756358493638142e-05,
      "loss": 0.0196,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.45252829790115356,
      "eval_runtime": 11.5175,
      "eval_samples_per_second": 325.591,
      "eval_steps_per_second": 5.123,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.10037428885698318,
      "learning_rate": 8.235669337084578e-06,
      "loss": 0.0048,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9029333333333334,
      "eval_loss": 0.3953802287578583,
      "eval_runtime": 11.1167,
      "eval_samples_per_second": 337.331,
      "eval_steps_per_second": 5.307,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.15734480321407318,
      "learning_rate": 2.135927015187301e-06,
      "loss": 0.0015,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9061333333333333,
      "eval_loss": 0.38626569509506226,
      "eval_runtime": 11.1377,
      "eval_samples_per_second": 336.693,
      "eval_steps_per_second": 5.297,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.013887502253055573,
      "learning_rate": 7.691731939263313e-11,
      "loss": 0.001,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9064,
      "eval_loss": 0.39700981974601746,
      "eval_runtime": 11.4114,
      "eval_samples_per_second": 328.619,
      "eval_steps_per_second": 5.17,
      "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
}