Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0812

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0812
File size: 4,310 Bytes 
7d87a5c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8808,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0812/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": 7e-05,
      "loss": 1.5836,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8197333333333333,
      "eval_loss": 0.6981914043426514,
      "eval_runtime": 5.7139,
      "eval_samples_per_second": 656.296,
      "eval_steps_per_second": 10.326,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.752187967300415,
      "learning_rate": 7e-05,
      "loss": 0.4798,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8461333333333333,
      "eval_loss": 0.5413401126861572,
      "eval_runtime": 5.6844,
      "eval_samples_per_second": 659.706,
      "eval_steps_per_second": 10.379,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.0596983432769775,
      "learning_rate": 7e-05,
      "loss": 0.264,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8498666666666667,
      "eval_loss": 0.5297785997390747,
      "eval_runtime": 5.6999,
      "eval_samples_per_second": 657.902,
      "eval_steps_per_second": 10.351,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3232392966747284,
      "learning_rate": 7e-05,
      "loss": 0.162,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8629333333333333,
      "eval_loss": 0.5003112554550171,
      "eval_runtime": 5.7861,
      "eval_samples_per_second": 648.104,
      "eval_steps_per_second": 10.197,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4661165475845337,
      "learning_rate": 7e-05,
      "loss": 0.1044,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8688,
      "eval_loss": 0.5113104581832886,
      "eval_runtime": 6.2381,
      "eval_samples_per_second": 601.144,
      "eval_steps_per_second": 9.458,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04030507802963257,
      "learning_rate": 7e-05,
      "loss": 0.0774,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8650666666666667,
      "eval_loss": 0.5112684369087219,
      "eval_runtime": 5.9463,
      "eval_samples_per_second": 630.643,
      "eval_steps_per_second": 9.922,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.02839038334786892,
      "learning_rate": 7e-05,
      "loss": 0.0594,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.5687946677207947,
      "eval_runtime": 5.738,
      "eval_samples_per_second": 653.542,
      "eval_steps_per_second": 10.282,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.02960929647088051,
      "learning_rate": 7e-05,
      "loss": 0.0518,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8669333333333333,
      "eval_loss": 0.5728327035903931,
      "eval_runtime": 5.847,
      "eval_samples_per_second": 641.36,
      "eval_steps_per_second": 10.091,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.5553554892539978,
      "learning_rate": 7e-05,
      "loss": 0.0498,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8808,
      "eval_loss": 0.5194405317306519,
      "eval_runtime": 5.7117,
      "eval_samples_per_second": 656.553,
      "eval_steps_per_second": 10.33,
      "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
}