Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0631

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0631
File size: 4,469 Bytes 
9d44dda
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9093333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0631/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": 6.790177189676492e-05,
      "loss": 1.6858,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7938666666666667,
      "eval_loss": 0.7781952023506165,
      "eval_runtime": 6.6093,
      "eval_samples_per_second": 567.384,
      "eval_steps_per_second": 8.927,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.732579231262207,
      "learning_rate": 6.183512375367748e-05,
      "loss": 0.4979,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8544,
      "eval_loss": 0.5089985728263855,
      "eval_runtime": 6.5307,
      "eval_samples_per_second": 574.215,
      "eval_steps_per_second": 9.034,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.014962077140808,
      "learning_rate": 5.253176364164983e-05,
      "loss": 0.2745,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8826666666666667,
      "eval_loss": 0.4169585108757019,
      "eval_runtime": 6.7302,
      "eval_samples_per_second": 557.193,
      "eval_steps_per_second": 8.767,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.843432068824768,
      "learning_rate": 4.1113814093164575e-05,
      "loss": 0.1511,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.39479291439056396,
      "eval_runtime": 7.4068,
      "eval_samples_per_second": 506.293,
      "eval_steps_per_second": 7.966,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5652885437011719,
      "learning_rate": 2.8958448334757455e-05,
      "loss": 0.0793,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8928,
      "eval_loss": 0.4081272780895233,
      "eval_runtime": 6.551,
      "eval_samples_per_second": 572.427,
      "eval_steps_per_second": 9.006,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.06498584151268005,
      "learning_rate": 1.7531782870984953e-05,
      "loss": 0.0369,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9053333333333333,
      "eval_loss": 0.35789909958839417,
      "eval_runtime": 6.5759,
      "eval_samples_per_second": 570.267,
      "eval_steps_per_second": 8.972,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.07514520734548569,
      "learning_rate": 8.212042196399656e-06,
      "loss": 0.0147,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9082666666666667,
      "eval_loss": 0.36298590898513794,
      "eval_runtime": 7.0314,
      "eval_samples_per_second": 533.32,
      "eval_steps_per_second": 8.391,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.05408753082156181,
      "learning_rate": 2.1233245810799825e-06,
      "loss": 0.007,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9074666666666666,
      "eval_loss": 0.3553488254547119,
      "eval_runtime": 6.5846,
      "eval_samples_per_second": 569.511,
      "eval_steps_per_second": 8.96,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.12669388949871063,
      "learning_rate": 1.9229335130876987e-11,
      "loss": 0.0053,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9093333333333333,
      "eval_loss": 0.35696542263031006,
      "eval_runtime": 6.5487,
      "eval_samples_per_second": 572.633,
      "eval_steps_per_second": 9.009,
      "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
}