Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0198

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0198
File size: 3,945 Bytes 
88dcbbf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8762666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0198/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 1.6557,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8069333333333333,
      "eval_loss": 0.7169371843338013,
      "eval_runtime": 6.7984,
      "eval_samples_per_second": 551.603,
      "eval_steps_per_second": 8.679,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.538965225219727,
      "learning_rate": 9e-05,
      "loss": 0.5211,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.5660959482192993,
      "eval_runtime": 7.5555,
      "eval_samples_per_second": 496.327,
      "eval_steps_per_second": 7.809,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.9417922496795654,
      "learning_rate": 9e-05,
      "loss": 0.3181,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8530666666666666,
      "eval_loss": 0.5210608839988708,
      "eval_runtime": 6.6965,
      "eval_samples_per_second": 559.992,
      "eval_steps_per_second": 8.811,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.921548068523407,
      "learning_rate": 9e-05,
      "loss": 0.2114,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8613333333333333,
      "eval_loss": 0.5168349742889404,
      "eval_runtime": 6.7674,
      "eval_samples_per_second": 554.129,
      "eval_steps_per_second": 8.718,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.1531,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8621333333333333,
      "eval_loss": 0.5049996972084045,
      "eval_runtime": 6.6848,
      "eval_samples_per_second": 560.978,
      "eval_steps_per_second": 8.826,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6599763035774231,
      "learning_rate": 9e-05,
      "loss": 0.1111,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.542316734790802,
      "eval_runtime": 6.7509,
      "eval_samples_per_second": 555.484,
      "eval_steps_per_second": 8.74,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.04530762508511543,
      "learning_rate": 9e-05,
      "loss": 0.0985,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8717333333333334,
      "eval_loss": 0.5089701414108276,
      "eval_runtime": 7.9269,
      "eval_samples_per_second": 473.071,
      "eval_steps_per_second": 7.443,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.3164353370666504,
      "learning_rate": 9e-05,
      "loss": 0.0757,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8762666666666666,
      "eval_loss": 0.47865772247314453,
      "eval_runtime": 6.8067,
      "eval_samples_per_second": 550.925,
      "eval_steps_per_second": 8.668,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}