Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0731

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0731
File size: 4,430 Bytes 
b60134c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9162666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0731/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": 8.223931312561035,
      "learning_rate": 8.728616793536588e-05,
      "loss": 1.4472,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7933333333333333,
      "eval_loss": 0.7200683355331421,
      "eval_runtime": 6.8407,
      "eval_samples_per_second": 548.187,
      "eval_steps_per_second": 8.625,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.95023019690139e-05,
      "loss": 0.4753,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8488,
      "eval_loss": 0.5139306783676147,
      "eval_runtime": 6.838,
      "eval_samples_per_second": 548.405,
      "eval_steps_per_second": 8.628,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.929837465286255,
      "learning_rate": 6.75408389678355e-05,
      "loss": 0.2738,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.876,
      "eval_loss": 0.4120531678199768,
      "eval_runtime": 7.1115,
      "eval_samples_per_second": 527.317,
      "eval_steps_per_second": 8.296,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12394455820322037,
      "learning_rate": 5.286061811978304e-05,
      "loss": 0.154,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.39220938086509705,
      "eval_runtime": 6.8012,
      "eval_samples_per_second": 551.376,
      "eval_steps_per_second": 8.675,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.23897947371006012,
      "learning_rate": 3.723229071611673e-05,
      "loss": 0.0775,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9026666666666666,
      "eval_loss": 0.363088995218277,
      "eval_runtime": 6.8414,
      "eval_samples_per_second": 548.136,
      "eval_steps_per_second": 8.624,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04011377692222595,
      "learning_rate": 2.2540863691266368e-05,
      "loss": 0.0356,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8965333333333333,
      "eval_loss": 0.38601166009902954,
      "eval_runtime": 7.5502,
      "eval_samples_per_second": 496.674,
      "eval_steps_per_second": 7.814,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.8657380938529968,
      "learning_rate": 1.055833996679956e-05,
      "loss": 0.0136,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9088,
      "eval_loss": 0.35430845618247986,
      "eval_runtime": 6.8544,
      "eval_samples_per_second": 547.097,
      "eval_steps_per_second": 8.608,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.06902644038200378,
      "learning_rate": 2.7299887471028354e-06,
      "loss": 0.0063,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9136,
      "eval_loss": 0.3435041010379791,
      "eval_runtime": 7.9235,
      "eval_samples_per_second": 473.274,
      "eval_steps_per_second": 7.446,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.15000472962856293,
      "learning_rate": 2.472343088255613e-11,
      "loss": 0.0044,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9162666666666667,
      "eval_loss": 0.33700811862945557,
      "eval_runtime": 6.7734,
      "eval_samples_per_second": 553.637,
      "eval_steps_per_second": 8.711,
      "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
}