Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0088

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0088
File size: 4,467 Bytes 
0d10be9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8893333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0088/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": 8.892225558892226e-05,
      "loss": 1.6067,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7762666666666667,
      "eval_loss": 0.7949973344802856,
      "eval_runtime": 13.5262,
      "eval_samples_per_second": 277.24,
      "eval_steps_per_second": 4.362,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 18.192279815673828,
      "learning_rate": 7.781114447781115e-05,
      "loss": 0.5399,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8330666666666666,
      "eval_loss": 0.5704893469810486,
      "eval_runtime": 13.1343,
      "eval_samples_per_second": 285.511,
      "eval_steps_per_second": 4.492,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.8463321924209595,
      "learning_rate": 6.670003336670004e-05,
      "loss": 0.3126,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8381333333333333,
      "eval_loss": 0.5220766663551331,
      "eval_runtime": 13.0391,
      "eval_samples_per_second": 287.597,
      "eval_steps_per_second": 4.525,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.21836727857589722,
      "learning_rate": 5.5588922255588925e-05,
      "loss": 0.1922,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8562666666666666,
      "eval_loss": 0.5017856359481812,
      "eval_runtime": 13.2819,
      "eval_samples_per_second": 282.34,
      "eval_steps_per_second": 4.442,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.335660934448242,
      "learning_rate": 4.447781114447781e-05,
      "loss": 0.1073,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.448233425617218,
      "eval_runtime": 13.0946,
      "eval_samples_per_second": 286.378,
      "eval_steps_per_second": 4.506,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.039736308157444,
      "learning_rate": 3.33667000333667e-05,
      "loss": 0.059,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8736,
      "eval_loss": 0.47666269540786743,
      "eval_runtime": 13.1037,
      "eval_samples_per_second": 286.178,
      "eval_steps_per_second": 4.503,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.3002619445323944,
      "learning_rate": 2.225558892225559e-05,
      "loss": 0.029,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.4393323063850403,
      "eval_runtime": 13.2408,
      "eval_samples_per_second": 283.215,
      "eval_steps_per_second": 4.456,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.4963516891002655,
      "learning_rate": 1.1144477811144478e-05,
      "loss": 0.012,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.44757968187332153,
      "eval_runtime": 13.3013,
      "eval_samples_per_second": 281.928,
      "eval_steps_per_second": 4.436,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.5708210468292236,
      "learning_rate": 3.3366700033366706e-08,
      "loss": 0.0058,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.4516837000846863,
      "eval_runtime": 13.542,
      "eval_samples_per_second": 276.916,
      "eval_steps_per_second": 4.357,
      "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
}