Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0997

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0997
File size: 3,682 Bytes 
2893152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.9250666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0997/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.2666495442390442,
      "learning_rate": 6.003003003003003e-05,
      "loss": 0.7895,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8621333333333333,
      "eval_loss": 0.45370209217071533,
      "eval_runtime": 12.1228,
      "eval_samples_per_second": 309.333,
      "eval_steps_per_second": 4.867,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.67689323425293,
      "learning_rate": 5.0030030030030024e-05,
      "loss": 0.2047,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.3958718180656433,
      "eval_runtime": 12.1505,
      "eval_samples_per_second": 308.63,
      "eval_steps_per_second": 4.856,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.013741959817707539,
      "learning_rate": 4.003003003003003e-05,
      "loss": 0.0962,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8752,
      "eval_loss": 0.44304198026657104,
      "eval_runtime": 11.862,
      "eval_samples_per_second": 316.136,
      "eval_steps_per_second": 4.974,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.012073731981217861,
      "learning_rate": 3.003003003003003e-05,
      "loss": 0.0433,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9032,
      "eval_loss": 0.3896464705467224,
      "eval_runtime": 11.9425,
      "eval_samples_per_second": 314.003,
      "eval_steps_per_second": 4.94,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.07638824731111526,
      "learning_rate": 2.003003003003003e-05,
      "loss": 0.0191,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9133333333333333,
      "eval_loss": 0.3630318343639374,
      "eval_runtime": 12.4185,
      "eval_samples_per_second": 301.969,
      "eval_steps_per_second": 4.751,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0001728335046209395,
      "learning_rate": 1.003003003003003e-05,
      "loss": 0.0031,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9189333333333334,
      "eval_loss": 0.34284478425979614,
      "eval_runtime": 11.9093,
      "eval_samples_per_second": 314.881,
      "eval_steps_per_second": 4.954,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.00447858078405261,
      "learning_rate": 3.0030030030030026e-08,
      "loss": 0.0012,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9250666666666667,
      "eval_loss": 0.3320516347885132,
      "eval_runtime": 13.3242,
      "eval_samples_per_second": 281.443,
      "eval_steps_per_second": 4.428,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}