Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0091

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0091
File size: 3,297 Bytes 
0041878
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8957333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0091/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": 20.237627029418945,
      "learning_rate": 6.533836810383375e-05,
      "loss": 1.5268,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8058666666666666,
      "eval_loss": 0.7096470594406128,
      "eval_runtime": 11.1513,
      "eval_samples_per_second": 336.283,
      "eval_steps_per_second": 5.291,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8086804151535034,
      "learning_rate": 5.2547638240566195e-05,
      "loss": 0.4348,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.4678380787372589,
      "eval_runtime": 11.3382,
      "eval_samples_per_second": 330.741,
      "eval_steps_per_second": 5.204,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6776532530784607,
      "learning_rate": 3.505503288166546e-05,
      "loss": 0.2076,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.42917585372924805,
      "eval_runtime": 11.0856,
      "eval_samples_per_second": 338.276,
      "eval_steps_per_second": 5.322,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.035297393798828,
      "learning_rate": 1.7595406161244655e-05,
      "loss": 0.0935,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8837333333333334,
      "eval_loss": 0.3958376348018646,
      "eval_runtime": 11.0584,
      "eval_samples_per_second": 339.108,
      "eval_steps_per_second": 5.335,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2946469485759735,
      "learning_rate": 4.744293558904729e-06,
      "loss": 0.0365,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8941333333333333,
      "eval_loss": 0.37826424837112427,
      "eval_runtime": 11.2129,
      "eval_samples_per_second": 334.437,
      "eval_steps_per_second": 5.262,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.5083849430084229,
      "learning_rate": 1.7306388939264393e-10,
      "loss": 0.0167,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8957333333333334,
      "eval_loss": 0.3767309784889221,
      "eval_runtime": 11.0805,
      "eval_samples_per_second": 338.433,
      "eval_steps_per_second": 5.325,
      "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
}