Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0301

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0301
File size: 3,650 Bytes 
4f245fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9045333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0301/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": 5.182464122772217,
      "learning_rate": 8.659485808097889e-05,
      "loss": 1.5493,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7954666666666667,
      "eval_loss": 0.7515386939048767,
      "eval_runtime": 13.8401,
      "eval_samples_per_second": 270.951,
      "eval_steps_per_second": 4.263,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.7990598678588867,
      "learning_rate": 7.685730736804761e-05,
      "loss": 0.5397,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8416,
      "eval_loss": 0.5320761799812317,
      "eval_runtime": 13.3843,
      "eval_samples_per_second": 280.18,
      "eval_steps_per_second": 4.408,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.6416701078414917,
      "learning_rate": 6.226977039554153e-05,
      "loss": 0.3294,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8493333333333334,
      "eval_loss": 0.48750919103622437,
      "eval_runtime": 13.5628,
      "eval_samples_per_second": 276.491,
      "eval_steps_per_second": 4.35,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.5030906200408936,
      "learning_rate": 4.505306743117272e-05,
      "loss": 0.1982,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.4356118142604828,
      "eval_runtime": 13.8584,
      "eval_samples_per_second": 270.594,
      "eval_steps_per_second": 4.257,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 2.7877349199942123e-05,
      "loss": 0.1155,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8888,
      "eval_loss": 0.3909323215484619,
      "eval_runtime": 13.3671,
      "eval_samples_per_second": 280.54,
      "eval_steps_per_second": 4.414,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6467602849006653,
      "learning_rate": 1.3255331978432106e-05,
      "loss": 0.059,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9016,
      "eval_loss": 0.38072097301483154,
      "eval_runtime": 13.3642,
      "eval_samples_per_second": 280.601,
      "eval_steps_per_second": 4.415,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0560840368270874,
      "learning_rate": 3.4661526970736e-06,
      "loss": 0.0305,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9045333333333333,
      "eval_loss": 0.3661123514175415,
      "eval_runtime": 13.5398,
      "eval_samples_per_second": 276.961,
      "eval_steps_per_second": 4.358,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}