Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0035

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0035
File size: 2,441 Bytes 
5d1f367
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.43733333333333335,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0035/checkpoints/checkpoint-1332",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1332,
  "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": 0.0004271931404387096,
      "loss": 3.2709,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1952,
      "eval_loss": 2.956878662109375,
      "eval_runtime": 5.4399,
      "eval_samples_per_second": 689.354,
      "eval_steps_per_second": 10.846,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.643,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.32506666666666667,
      "eval_loss": 2.451343297958374,
      "eval_runtime": 5.391,
      "eval_samples_per_second": 695.604,
      "eval_steps_per_second": 10.944,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 7.447853104434438e-05,
      "loss": 2.1452,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.40853333333333336,
      "eval_loss": 2.065028667449951,
      "eval_runtime": 5.5093,
      "eval_samples_per_second": 680.668,
      "eval_steps_per_second": 10.709,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.93427848815918,
      "learning_rate": 6.258092905636614e-09,
      "loss": 1.6923,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.43733333333333335,
      "eval_loss": 1.9389710426330566,
      "eval_runtime": 5.3426,
      "eval_samples_per_second": 701.91,
      "eval_steps_per_second": 11.043,
      "step": 1332
    }
  ],
  "logging_steps": 500,
  "max_steps": 1332,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 6.58965282490368e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}