Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0675

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0675
File size: 3,642 Bytes 
2ab0b5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
{
  "best_metric": 0.9029333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0675/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "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": 8.575718575718577e-05,
      "loss": 2.0987,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7525333333333334,
      "eval_loss": 0.8478028178215027,
      "eval_runtime": 6.6775,
      "eval_samples_per_second": 561.591,
      "eval_steps_per_second": 8.836,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.880056858062744,
      "learning_rate": 7.147147147147148e-05,
      "loss": 0.6115,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8288,
      "eval_loss": 0.573768675327301,
      "eval_runtime": 6.7098,
      "eval_samples_per_second": 558.886,
      "eval_steps_per_second": 8.793,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.48056697845459,
      "learning_rate": 5.718575718575719e-05,
      "loss": 0.3455,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.4669803977012634,
      "eval_runtime": 6.3894,
      "eval_samples_per_second": 586.91,
      "eval_steps_per_second": 9.234,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.005107879638672,
      "learning_rate": 4.2900042900042906e-05,
      "loss": 0.2063,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8845333333333333,
      "eval_loss": 0.384105920791626,
      "eval_runtime": 6.4959,
      "eval_samples_per_second": 577.287,
      "eval_steps_per_second": 9.083,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.4089245796203613,
      "learning_rate": 2.8614328614328617e-05,
      "loss": 0.1272,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.39325112104415894,
      "eval_runtime": 6.4075,
      "eval_samples_per_second": 585.251,
      "eval_steps_per_second": 9.208,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2161138355731964,
      "learning_rate": 1.4328614328614328e-05,
      "loss": 0.0672,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8944,
      "eval_loss": 0.367453932762146,
      "eval_runtime": 6.3798,
      "eval_samples_per_second": 587.792,
      "eval_steps_per_second": 9.248,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.11173789203166962,
      "learning_rate": 4.2900042900042903e-08,
      "loss": 0.0331,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9029333333333334,
      "eval_loss": 0.34063541889190674,
      "eval_runtime": 6.5806,
      "eval_samples_per_second": 569.858,
      "eval_steps_per_second": 8.966,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}