Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0234

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0234
File size: 3,932 Bytes 
76e44fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.368,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0234/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": Infinity,
      "learning_rate": 0.0005,
      "loss": 3.3874,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19546666666666668,
      "eval_loss": 2.9785778522491455,
      "eval_runtime": 4.6739,
      "eval_samples_per_second": 802.328,
      "eval_steps_per_second": 12.623,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.855402946472168,
      "learning_rate": 0.0005,
      "loss": 2.8765,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.25466666666666665,
      "eval_loss": 2.7459378242492676,
      "eval_runtime": 4.8204,
      "eval_samples_per_second": 777.949,
      "eval_steps_per_second": 12.24,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 11.855588912963867,
      "learning_rate": 0.0005,
      "loss": 2.7009,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.26453333333333334,
      "eval_loss": 2.7397959232330322,
      "eval_runtime": 4.4828,
      "eval_samples_per_second": 836.529,
      "eval_steps_per_second": 13.161,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.0883846282959,
      "learning_rate": 0.0005,
      "loss": 2.5848,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3042666666666667,
      "eval_loss": 2.597876787185669,
      "eval_runtime": 4.8193,
      "eval_samples_per_second": 778.128,
      "eval_steps_per_second": 12.243,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 10.812724113464355,
      "learning_rate": 0.0005,
      "loss": 2.4646,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.31333333333333335,
      "eval_loss": 2.4852473735809326,
      "eval_runtime": 4.7145,
      "eval_samples_per_second": 795.426,
      "eval_steps_per_second": 12.515,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 12.185145378112793,
      "learning_rate": 0.0005,
      "loss": 2.3939,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.33386666666666664,
      "eval_loss": 2.419703483581543,
      "eval_runtime": 4.7965,
      "eval_samples_per_second": 781.817,
      "eval_steps_per_second": 12.301,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.848531723022461,
      "learning_rate": 0.0005,
      "loss": 2.3126,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3576,
      "eval_loss": 2.320425510406494,
      "eval_runtime": 4.8248,
      "eval_samples_per_second": 777.242,
      "eval_steps_per_second": 12.229,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 13.888565063476562,
      "learning_rate": 0.0005,
      "loss": 2.2291,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.368,
      "eval_loss": 2.3137896060943604,
      "eval_runtime": 4.8654,
      "eval_samples_per_second": 770.746,
      "eval_steps_per_second": 12.126,
      "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
}