Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0912

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0912
File size: 4,446 Bytes 
be45b4f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.43306666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0912/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": 0.00048527961022201525,
      "loss": 3.3977,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20853333333333332,
      "eval_loss": 2.9758739471435547,
      "eval_runtime": 13.3572,
      "eval_samples_per_second": 280.748,
      "eval_steps_per_second": 4.417,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 24.03614044189453,
      "learning_rate": 0.0004421832247293072,
      "loss": 2.9123,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2528,
      "eval_loss": 2.784506320953369,
      "eval_runtime": 14.007,
      "eval_samples_per_second": 267.723,
      "eval_steps_per_second": 4.212,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.787612915039062,
      "learning_rate": 0.00037590670601192445,
      "loss": 2.7092,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.30506666666666665,
      "eval_loss": 2.545164108276367,
      "eval_runtime": 13.9157,
      "eval_samples_per_second": 269.48,
      "eval_steps_per_second": 4.24,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 37.62464904785156,
      "learning_rate": 0.00029444398036442514,
      "loss": 2.5168,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3264,
      "eval_loss": 2.4449145793914795,
      "eval_runtime": 13.316,
      "eval_samples_per_second": 281.616,
      "eval_steps_per_second": 4.431,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 23.430572509765625,
      "learning_rate": 0.00020762065476168375,
      "loss": 2.3305,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.35813333333333336,
      "eval_loss": 2.3044354915618896,
      "eval_runtime": 13.404,
      "eval_samples_per_second": 279.767,
      "eval_steps_per_second": 4.402,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 32.56107711791992,
      "learning_rate": 0.00012590890364720656,
      "loss": 2.1447,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3888,
      "eval_loss": 2.224315643310547,
      "eval_runtime": 12.8477,
      "eval_samples_per_second": 291.88,
      "eval_steps_per_second": 4.592,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 25.95368766784668,
      "learning_rate": 5.9164370142409884e-05,
      "loss": 1.9583,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.40746666666666664,
      "eval_loss": 2.119793176651001,
      "eval_runtime": 13.3082,
      "eval_samples_per_second": 281.78,
      "eval_steps_per_second": 4.433,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 1.5528220942544385e-05,
      "loss": 1.7776,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.43173333333333336,
      "eval_loss": 2.0774717330932617,
      "eval_runtime": 13.4944,
      "eval_samples_per_second": 277.894,
      "eval_steps_per_second": 4.372,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 20.68040657043457,
      "learning_rate": 3.433802298419275e-09,
      "loss": 1.6681,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.43306666666666666,
      "eval_loss": 2.080409288406372,
      "eval_runtime": 13.4648,
      "eval_samples_per_second": 278.505,
      "eval_steps_per_second": 4.382,
      "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
}