Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0621

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0621
File size: 2,849 Bytes 
159ae74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8936,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0621/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 4.525311529382417e-05,
      "loss": 1.9338,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7893333333333333,
      "eval_loss": 0.8721290230751038,
      "eval_runtime": 4.1011,
      "eval_samples_per_second": 914.399,
      "eval_steps_per_second": 14.387,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.598394393920898,
      "learning_rate": 3.277027342564428e-05,
      "loss": 0.5406,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8522666666666666,
      "eval_loss": 0.5168169140815735,
      "eval_runtime": 4.0669,
      "eval_samples_per_second": 922.079,
      "eval_steps_per_second": 14.507,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5857601165771484,
      "learning_rate": 1.731945121074836e-05,
      "loss": 0.2234,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.417741596698761,
      "eval_runtime": 4.0485,
      "eval_samples_per_second": 926.261,
      "eval_steps_per_second": 14.573,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2547053396701813,
      "learning_rate": 4.802337581094707e-06,
      "loss": 0.0882,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8909333333333334,
      "eval_loss": 0.37163209915161133,
      "eval_runtime": 4.5471,
      "eval_samples_per_second": 824.693,
      "eval_steps_per_second": 12.975,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7757229208946228,
      "learning_rate": 4.4502166460236305e-11,
      "loss": 0.0427,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8936,
      "eval_loss": 0.3642432689666748,
      "eval_runtime": 4.0209,
      "eval_samples_per_second": 932.637,
      "eval_steps_per_second": 14.673,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}