Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0311

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0311
File size: 4,480 Bytes 
b47dd32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.9213333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0311/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "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": 6.224557891224557e-05,
      "loss": 1.9259,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8170666666666667,
      "eval_loss": 0.7079011797904968,
      "eval_runtime": 7.2673,
      "eval_samples_per_second": 516.011,
      "eval_steps_per_second": 8.119,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.054899215698242,
      "learning_rate": 5.44678011344678e-05,
      "loss": 0.4835,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8733333333333333,
      "eval_loss": 0.4545210897922516,
      "eval_runtime": 6.5551,
      "eval_samples_per_second": 572.07,
      "eval_steps_per_second": 9.001,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3537403643131256,
      "learning_rate": 4.669002335669002e-05,
      "loss": 0.2483,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.39225897192955017,
      "eval_runtime": 6.587,
      "eval_samples_per_second": 569.302,
      "eval_steps_per_second": 8.957,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.24307934939861298,
      "learning_rate": 3.891224557891224e-05,
      "loss": 0.1373,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8973333333333333,
      "eval_loss": 0.34796974062919617,
      "eval_runtime": 6.7479,
      "eval_samples_per_second": 555.729,
      "eval_steps_per_second": 8.743,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.30246680974960327,
      "learning_rate": 3.113446780113447e-05,
      "loss": 0.0744,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8954666666666666,
      "eval_loss": 0.3674723207950592,
      "eval_runtime": 8.0829,
      "eval_samples_per_second": 463.942,
      "eval_steps_per_second": 7.299,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.09988828748464584,
      "learning_rate": 2.3356690023356685e-05,
      "loss": 0.0363,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9096,
      "eval_loss": 0.3321395218372345,
      "eval_runtime": 6.6412,
      "eval_samples_per_second": 564.657,
      "eval_steps_per_second": 8.884,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03556036949157715,
      "learning_rate": 1.557891224557891e-05,
      "loss": 0.017,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9101333333333333,
      "eval_loss": 0.3302697241306305,
      "eval_runtime": 6.5455,
      "eval_samples_per_second": 572.911,
      "eval_steps_per_second": 9.014,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.15674729645252228,
      "learning_rate": 7.801134467801133e-06,
      "loss": 0.0078,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9205333333333333,
      "eval_loss": 0.31443047523498535,
      "eval_runtime": 6.5266,
      "eval_samples_per_second": 574.574,
      "eval_steps_per_second": 9.04,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.16684173047542572,
      "learning_rate": 2.3356690023356688e-08,
      "loss": 0.005,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9213333333333333,
      "eval_loss": 0.3068985044956207,
      "eval_runtime": 6.6753,
      "eval_samples_per_second": 561.772,
      "eval_steps_per_second": 8.839,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}