Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0640

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0640
File size: 2,856 Bytes 
f0a624d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8869333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0640/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": 2.85232922088503e-05,
      "loss": 2.207,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7616,
      "eval_loss": 1.0240451097488403,
      "eval_runtime": 13.3479,
      "eval_samples_per_second": 280.944,
      "eval_steps_per_second": 4.42,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.4383924288793503e-05,
      "loss": 0.7309,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8301333333333333,
      "eval_loss": 0.6050614714622498,
      "eval_runtime": 13.5862,
      "eval_samples_per_second": 276.016,
      "eval_steps_per_second": 4.343,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 30.860454559326172,
      "learning_rate": 1.837722045066209e-05,
      "loss": 0.4433,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.5174089074134827,
      "eval_runtime": 13.7958,
      "eval_samples_per_second": 271.821,
      "eval_steps_per_second": 4.277,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.3314332962036133,
      "learning_rate": 1.1701616683386336e-05,
      "loss": 0.2958,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.4238029420375824,
      "eval_runtime": 13.6254,
      "eval_samples_per_second": 275.221,
      "eval_steps_per_second": 4.33,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.105777740478516,
      "learning_rate": 5.679298183982636e-06,
      "loss": 0.2093,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8869333333333334,
      "eval_loss": 0.39692923426628113,
      "eval_runtime": 13.6485,
      "eval_samples_per_second": 274.756,
      "eval_steps_per_second": 4.323,
      "step": 1665
    }
  ],
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}