Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0413

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0413
File size: 4,064 Bytes 
811c822
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9328,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0413/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.739501476287842,
      "learning_rate": 4.8108254489432715e-05,
      "loss": 0.7689,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8813333333333333,
      "eval_loss": 0.4020669162273407,
      "eval_runtime": 6.9193,
      "eval_samples_per_second": 541.965,
      "eval_steps_per_second": 8.527,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.31422245502471924,
      "learning_rate": 4.2698504093359784e-05,
      "loss": 0.2311,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.3809215724468231,
      "eval_runtime": 6.2774,
      "eval_samples_per_second": 597.381,
      "eval_steps_per_second": 9.399,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": NaN,
      "learning_rate": 3.4621534620947785e-05,
      "loss": 0.1175,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9037333333333334,
      "eval_loss": 0.34594160318374634,
      "eval_runtime": 6.2555,
      "eval_samples_per_second": 599.474,
      "eval_steps_per_second": 9.432,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4958207607269287,
      "learning_rate": 2.5058963771413844e-05,
      "loss": 0.0552,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9117333333333333,
      "eval_loss": 0.33816301822662354,
      "eval_runtime": 6.2534,
      "eval_samples_per_second": 599.671,
      "eval_steps_per_second": 9.435,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.49200737476348877,
      "learning_rate": 1.5487416222190068e-05,
      "loss": 0.0236,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9253333333333333,
      "eval_loss": 0.2933698892593384,
      "eval_runtime": 6.5464,
      "eval_samples_per_second": 572.83,
      "eval_steps_per_second": 9.013,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1695154458284378,
      "learning_rate": 7.36407332135117e-06,
      "loss": 0.0073,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.29496312141418457,
      "eval_runtime": 6.6619,
      "eval_samples_per_second": 562.899,
      "eval_steps_per_second": 8.856,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.00972589012235403,
      "learning_rate": 1.925640387263111e-06,
      "loss": 0.0024,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9282666666666667,
      "eval_loss": 0.29633039236068726,
      "eval_runtime": 6.2585,
      "eval_samples_per_second": 599.186,
      "eval_steps_per_second": 9.427,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0015249729622155428,
      "learning_rate": 6.953462348691098e-11,
      "loss": 0.0009,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.2863103449344635,
      "eval_runtime": 6.3313,
      "eval_samples_per_second": 592.3,
      "eval_steps_per_second": 9.319,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}