Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0561

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0561
File size: 4,443 Bytes 
d6988b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8925333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0561/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": 1.6584,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8069333333333333,
      "eval_loss": 0.7102803587913513,
      "eval_runtime": 7.0041,
      "eval_samples_per_second": 535.399,
      "eval_steps_per_second": 8.424,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.449115782449115e-05,
      "loss": 0.4737,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8464,
      "eval_loss": 0.5213052034378052,
      "eval_runtime": 5.7433,
      "eval_samples_per_second": 652.929,
      "eval_steps_per_second": 10.273,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.700541496276855,
      "learning_rate": 4.671338004671337e-05,
      "loss": 0.2378,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8552,
      "eval_loss": 0.4766324758529663,
      "eval_runtime": 5.8525,
      "eval_samples_per_second": 640.748,
      "eval_steps_per_second": 10.081,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.10377110540866852,
      "learning_rate": 3.89356022689356e-05,
      "loss": 0.1209,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8722666666666666,
      "eval_loss": 0.4287908673286438,
      "eval_runtime": 5.7168,
      "eval_samples_per_second": 655.96,
      "eval_steps_per_second": 10.32,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1364617943763733,
      "learning_rate": 3.115782449115782e-05,
      "loss": 0.0548,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8818666666666667,
      "eval_loss": 0.43714746832847595,
      "eval_runtime": 7.2643,
      "eval_samples_per_second": 516.225,
      "eval_steps_per_second": 8.122,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2943328619003296,
      "learning_rate": 2.3380046713380048e-05,
      "loss": 0.0232,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8848,
      "eval_loss": 0.4423528015613556,
      "eval_runtime": 5.8465,
      "eval_samples_per_second": 641.406,
      "eval_steps_per_second": 10.091,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.049546774476766586,
      "learning_rate": 1.5602268935602267e-05,
      "loss": 0.0075,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.4610310196876526,
      "eval_runtime": 5.7016,
      "eval_samples_per_second": 657.709,
      "eval_steps_per_second": 10.348,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.032921869307756424,
      "learning_rate": 7.824491157824491e-06,
      "loss": 0.0037,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8912,
      "eval_loss": 0.43598607182502747,
      "eval_runtime": 7.2724,
      "eval_samples_per_second": 515.646,
      "eval_steps_per_second": 8.113,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.02152385748922825,
      "learning_rate": 4.6713380046713376e-08,
      "loss": 0.0025,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8925333333333333,
      "eval_loss": 0.4387677311897278,
      "eval_runtime": 5.7653,
      "eval_samples_per_second": 650.444,
      "eval_steps_per_second": 10.234,
      "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
}