Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0484

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__DINO__model_idx_0484
File size: 3,160 Bytes 
5a75fe1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8610666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0484/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.6088770627975464,
      "learning_rate": 0.0001,
      "loss": 0.8766,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8458666666666667,
      "eval_loss": 0.525999128818512,
      "eval_runtime": 12.8622,
      "eval_samples_per_second": 291.551,
      "eval_steps_per_second": 4.587,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.631195068359375,
      "learning_rate": 0.0001,
      "loss": 0.323,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8472,
      "eval_loss": 0.5741825699806213,
      "eval_runtime": 12.489,
      "eval_samples_per_second": 300.265,
      "eval_steps_per_second": 4.724,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 57.036598205566406,
      "learning_rate": 0.0001,
      "loss": 0.2181,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8354666666666667,
      "eval_loss": 0.6272071599960327,
      "eval_runtime": 12.4518,
      "eval_samples_per_second": 301.161,
      "eval_steps_per_second": 4.738,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 141.3208770751953,
      "learning_rate": 0.0001,
      "loss": 0.1643,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8504,
      "eval_loss": 0.576921284198761,
      "eval_runtime": 12.2754,
      "eval_samples_per_second": 305.489,
      "eval_steps_per_second": 4.806,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.950174331665039,
      "learning_rate": 0.0001,
      "loss": 0.133,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8232,
      "eval_loss": 0.7556498646736145,
      "eval_runtime": 12.8094,
      "eval_samples_per_second": 292.753,
      "eval_steps_per_second": 4.606,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6027507185935974,
      "learning_rate": 0.0001,
      "loss": 0.1277,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.5643792748451233,
      "eval_runtime": 12.2736,
      "eval_samples_per_second": 305.533,
      "eval_steps_per_second": 4.807,
      "step": 1998
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}