Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0501

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0501
File size: 3,165 Bytes 
b326326
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8514666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0501/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": 0.0001,
      "loss": 1.5948,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7936,
      "eval_loss": 0.7195043563842773,
      "eval_runtime": 13.1778,
      "eval_samples_per_second": 284.569,
      "eval_steps_per_second": 4.477,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 19.709989547729492,
      "learning_rate": 0.0001,
      "loss": 0.5422,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8125333333333333,
      "eval_loss": 0.6134871244430542,
      "eval_runtime": 13.2742,
      "eval_samples_per_second": 282.503,
      "eval_steps_per_second": 4.445,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.037708759307861,
      "learning_rate": 0.0001,
      "loss": 0.3427,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8333333333333334,
      "eval_loss": 0.5470404028892517,
      "eval_runtime": 13.1033,
      "eval_samples_per_second": 286.187,
      "eval_steps_per_second": 4.503,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.684505462646484,
      "learning_rate": 0.0001,
      "loss": 0.235,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8434666666666667,
      "eval_loss": 0.5833120942115784,
      "eval_runtime": 13.0467,
      "eval_samples_per_second": 287.429,
      "eval_steps_per_second": 4.522,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7275097966194153,
      "learning_rate": 0.0001,
      "loss": 0.174,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8392,
      "eval_loss": 0.5972058773040771,
      "eval_runtime": 13.0871,
      "eval_samples_per_second": 286.541,
      "eval_steps_per_second": 4.508,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.8389327526092529,
      "learning_rate": 0.0001,
      "loss": 0.1339,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8514666666666667,
      "eval_loss": 0.5725792050361633,
      "eval_runtime": 13.1999,
      "eval_samples_per_second": 284.092,
      "eval_steps_per_second": 4.47,
      "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
}