Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0883

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0883
File size: 3,255 Bytes 
85cce28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8930666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0883/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": 2.8002157758785897e-05,
      "loss": 2.2537,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7573333333333333,
      "eval_loss": 1.086980938911438,
      "eval_runtime": 6.3263,
      "eval_samples_per_second": 592.761,
      "eval_steps_per_second": 9.326,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.2540814184580827e-05,
      "loss": 0.7495,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8408,
      "eval_loss": 0.6406897306442261,
      "eval_runtime": 6.2655,
      "eval_samples_per_second": 598.519,
      "eval_steps_per_second": 9.417,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.352535247802734,
      "learning_rate": 1.5047170983116048e-05,
      "loss": 0.4432,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8682666666666666,
      "eval_loss": 0.490409255027771,
      "eval_runtime": 6.3003,
      "eval_samples_per_second": 595.212,
      "eval_steps_per_second": 9.365,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 17.223739624023438,
      "learning_rate": 7.5408883548191384e-06,
      "loss": 0.2978,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.41855695843696594,
      "eval_runtime": 6.8169,
      "eval_samples_per_second": 550.101,
      "eval_steps_per_second": 8.655,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 72.40629577636719,
      "learning_rate": 2.0332686681020267e-06,
      "loss": 0.219,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8890666666666667,
      "eval_loss": 0.38787031173706055,
      "eval_runtime": 6.7427,
      "eval_samples_per_second": 556.156,
      "eval_steps_per_second": 8.75,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 7.82125997543335,
      "learning_rate": 7.417023831113313e-11,
      "loss": 0.1801,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.38256385922431946,
      "eval_runtime": 6.977,
      "eval_samples_per_second": 537.481,
      "eval_steps_per_second": 8.456,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}