Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0729

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0729
File size: 4,036 Bytes 
e48c128
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8936,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0729/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": 4.119430065155029,
      "learning_rate": 8.75e-05,
      "loss": 1.6116,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7845333333333333,
      "eval_loss": 0.7278038263320923,
      "eval_runtime": 11.3065,
      "eval_samples_per_second": 331.669,
      "eval_steps_per_second": 5.218,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.503753753753753e-05,
      "loss": 0.5547,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5174999833106995,
      "eval_runtime": 11.4307,
      "eval_samples_per_second": 328.064,
      "eval_steps_per_second": 5.162,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8732233643531799,
      "learning_rate": 6.253753753753754e-05,
      "loss": 0.3389,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8512,
      "eval_loss": 0.49483224749565125,
      "eval_runtime": 11.4785,
      "eval_samples_per_second": 326.697,
      "eval_steps_per_second": 5.14,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.191214919090271,
      "learning_rate": 5.0037537537537535e-05,
      "loss": 0.2163,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.414200097322464,
      "eval_runtime": 12.4894,
      "eval_samples_per_second": 300.254,
      "eval_steps_per_second": 4.724,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 3.7575075075075075e-05,
      "loss": 0.1455,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.4029225707054138,
      "eval_runtime": 11.6054,
      "eval_samples_per_second": 323.125,
      "eval_steps_per_second": 5.084,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.05463141202926636,
      "learning_rate": 2.5075075075075076e-05,
      "loss": 0.0818,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.39706191420555115,
      "eval_runtime": 12.1816,
      "eval_samples_per_second": 307.842,
      "eval_steps_per_second": 4.843,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.6138795614242554,
      "learning_rate": 1.2575075075075077e-05,
      "loss": 0.045,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8885333333333333,
      "eval_loss": 0.4032522141933441,
      "eval_runtime": 11.2731,
      "eval_samples_per_second": 332.651,
      "eval_steps_per_second": 5.234,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.06299254298210144,
      "learning_rate": 7.507507507507508e-08,
      "loss": 0.0229,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8936,
      "eval_loss": 0.40311023592948914,
      "eval_runtime": 11.6485,
      "eval_samples_per_second": 321.93,
      "eval_steps_per_second": 5.065,
      "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
}