Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0265

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0265
File size: 2,819 Bytes 
b99ce64
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8984,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0265/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": Infinity,
      "learning_rate": 4.525311529382417e-05,
      "loss": 2.1629,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7941333333333334,
      "eval_loss": 0.813869297504425,
      "eval_runtime": 6.5442,
      "eval_samples_per_second": 573.028,
      "eval_steps_per_second": 9.016,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3.281509432839476e-05,
      "loss": 0.526,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8621333333333333,
      "eval_loss": 0.47640305757522583,
      "eval_runtime": 6.2806,
      "eval_samples_per_second": 597.081,
      "eval_steps_per_second": 9.394,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 36.96337890625,
      "learning_rate": 1.736435462495525e-05,
      "loss": 0.2642,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8813333333333333,
      "eval_loss": 0.3946755528450012,
      "eval_runtime": 6.0735,
      "eval_samples_per_second": 617.441,
      "eval_steps_per_second": 9.714,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5428288578987122,
      "learning_rate": 4.8301719287419e-06,
      "loss": 0.1407,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8936,
      "eval_loss": 0.3482056260108948,
      "eval_runtime": 6.1576,
      "eval_samples_per_second": 609.007,
      "eval_steps_per_second": 9.582,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.660046100616455,
      "learning_rate": 1.7800850740101738e-10,
      "loss": 0.0876,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8984,
      "eval_loss": 0.3448052704334259,
      "eval_runtime": 6.147,
      "eval_samples_per_second": 610.058,
      "eval_steps_per_second": 9.598,
      "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
}