Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0626

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0626
File size: 3,259 Bytes 
f6126cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8962666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0626/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": Infinity,
      "learning_rate": 2.85232922088503e-05,
      "loss": 2.239,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7712,
      "eval_loss": 1.0354540348052979,
      "eval_runtime": 5.9114,
      "eval_samples_per_second": 634.37,
      "eval_steps_per_second": 9.981,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.4383924288793503e-05,
      "loss": 0.7165,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8405333333333334,
      "eval_loss": 0.6178138256072998,
      "eval_runtime": 5.8241,
      "eval_samples_per_second": 643.873,
      "eval_steps_per_second": 10.13,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0150665044784546,
      "learning_rate": 1.837722045066209e-05,
      "loss": 0.4009,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.4571293890476227,
      "eval_runtime": 6.1387,
      "eval_samples_per_second": 610.878,
      "eval_steps_per_second": 9.611,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7099918723106384,
      "learning_rate": 1.1701616683386336e-05,
      "loss": 0.2482,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.42061367630958557,
      "eval_runtime": 5.8599,
      "eval_samples_per_second": 639.938,
      "eval_steps_per_second": 10.068,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.2909865379333496,
      "learning_rate": 5.679298183982636e-06,
      "loss": 0.1562,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.3924807906150818,
      "eval_runtime": 5.9277,
      "eval_samples_per_second": 632.622,
      "eval_steps_per_second": 9.953,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9158331751823425,
      "learning_rate": 1.5030589901472829e-06,
      "loss": 0.1044,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8962666666666667,
      "eval_loss": 0.38262051343917847,
      "eval_runtime": 5.9632,
      "eval_samples_per_second": 628.854,
      "eval_steps_per_second": 9.894,
      "step": 1998
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}