Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0848

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0848
File size: 4,308 Bytes 
8ec69a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8725333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0848/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": 9e-05,
      "loss": 1.5771,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8008,
      "eval_loss": 0.6988142132759094,
      "eval_runtime": 11.4578,
      "eval_samples_per_second": 327.289,
      "eval_steps_per_second": 5.149,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.5533,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8389333333333333,
      "eval_loss": 0.5396115779876709,
      "eval_runtime": 11.4353,
      "eval_samples_per_second": 327.932,
      "eval_steps_per_second": 5.159,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.3696,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8509333333333333,
      "eval_loss": 0.4841756820678711,
      "eval_runtime": 15.8709,
      "eval_samples_per_second": 236.281,
      "eval_steps_per_second": 3.717,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 34.43120574951172,
      "learning_rate": 9e-05,
      "loss": 0.2763,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8488,
      "eval_loss": 0.49039486050605774,
      "eval_runtime": 11.7191,
      "eval_samples_per_second": 319.992,
      "eval_steps_per_second": 5.035,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.594189167022705,
      "learning_rate": 9e-05,
      "loss": 0.2088,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8394666666666667,
      "eval_loss": 0.5290727019309998,
      "eval_runtime": 11.2035,
      "eval_samples_per_second": 334.717,
      "eval_steps_per_second": 5.266,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.9813108444213867,
      "learning_rate": 9e-05,
      "loss": 0.1656,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8677333333333334,
      "eval_loss": 0.4695935845375061,
      "eval_runtime": 11.2573,
      "eval_samples_per_second": 333.116,
      "eval_steps_per_second": 5.241,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03074013814330101,
      "learning_rate": 9e-05,
      "loss": 0.1392,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8549333333333333,
      "eval_loss": 0.5305938124656677,
      "eval_runtime": 11.5122,
      "eval_samples_per_second": 325.742,
      "eval_steps_per_second": 5.125,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.632561445236206,
      "learning_rate": 9e-05,
      "loss": 0.1221,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.49276694655418396,
      "eval_runtime": 11.1611,
      "eval_samples_per_second": 335.99,
      "eval_steps_per_second": 5.286,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.12701308727264404,
      "learning_rate": 9e-05,
      "loss": 0.1015,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.4889490008354187,
      "eval_runtime": 11.2019,
      "eval_samples_per_second": 334.766,
      "eval_steps_per_second": 5.267,
      "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
}