Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0497

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0497
File size: 4,059 Bytes 
04ae55d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
{
  "best_metric": 0.46746666666666664,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0497/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 0.0004850126564054637,
      "loss": 3.4022,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1712,
      "eval_loss": 3.1621155738830566,
      "eval_runtime": 6.2445,
      "eval_samples_per_second": 600.53,
      "eval_steps_per_second": 9.448,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 9.471333503723145,
      "learning_rate": 0.0004416794553834106,
      "loss": 2.9585,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.22186666666666666,
      "eval_loss": 2.8797731399536133,
      "eval_runtime": 6.3919,
      "eval_samples_per_second": 586.681,
      "eval_steps_per_second": 9.23,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003754536287075859,
      "loss": 2.6382,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.32506666666666667,
      "eval_loss": 2.4861209392547607,
      "eval_runtime": 6.3611,
      "eval_samples_per_second": 589.517,
      "eval_steps_per_second": 9.275,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.905771255493164,
      "learning_rate": 0.000293928108928647,
      "loss": 2.3155,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.36693333333333333,
      "eval_loss": 2.2996060848236084,
      "eval_runtime": 6.6234,
      "eval_samples_per_second": 566.176,
      "eval_steps_per_second": 8.908,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.878047943115234,
      "learning_rate": 0.00020710421090307243,
      "loss": 1.9694,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.41413333333333335,
      "eval_loss": 2.106428861618042,
      "eval_runtime": 6.1559,
      "eval_samples_per_second": 609.171,
      "eval_steps_per_second": 9.584,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 13.635309219360352,
      "learning_rate": 0.00012545417811701015,
      "loss": 1.5479,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4514666666666667,
      "eval_loss": 2.0253474712371826,
      "eval_runtime": 5.8103,
      "eval_samples_per_second": 645.406,
      "eval_steps_per_second": 10.154,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 5.899518490663266e-05,
      "loss": 1.0465,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.45893333333333336,
      "eval_loss": 2.0355722904205322,
      "eval_runtime": 5.7364,
      "eval_samples_per_second": 653.724,
      "eval_steps_per_second": 10.285,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 11.70781421661377,
      "learning_rate": 1.534689686405272e-05,
      "loss": 0.5767,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.46746666666666664,
      "eval_loss": 2.0783934593200684,
      "eval_runtime": 5.7911,
      "eval_samples_per_second": 647.549,
      "eval_steps_per_second": 10.188,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}