Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0668

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0668
File size: 4,041 Bytes 
0e908c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8869333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0668/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": 8.892225558892226e-05,
      "loss": 2.7175,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7194666666666667,
      "eval_loss": 1.0971484184265137,
      "eval_runtime": 6.4954,
      "eval_samples_per_second": 577.328,
      "eval_steps_per_second": 9.083,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.6905517578125,
      "learning_rate": 7.781114447781115e-05,
      "loss": 0.7238,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8176,
      "eval_loss": 0.6265469789505005,
      "eval_runtime": 6.1012,
      "eval_samples_per_second": 614.636,
      "eval_steps_per_second": 9.67,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 6.67334000667334e-05,
      "loss": 0.3553,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8544,
      "eval_loss": 0.49955958127975464,
      "eval_runtime": 6.1905,
      "eval_samples_per_second": 605.766,
      "eval_steps_per_second": 9.531,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 11.842399597167969,
      "learning_rate": 5.562228895562229e-05,
      "loss": 0.1986,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.5309600234031677,
      "eval_runtime": 6.1193,
      "eval_samples_per_second": 612.811,
      "eval_steps_per_second": 9.642,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.716106653213501,
      "learning_rate": 4.451117784451118e-05,
      "loss": 0.1098,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8685333333333334,
      "eval_loss": 0.4931130111217499,
      "eval_runtime": 6.0311,
      "eval_samples_per_second": 621.776,
      "eval_steps_per_second": 9.783,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07650568336248398,
      "learning_rate": 3.340006673340007e-05,
      "loss": 0.0635,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.4923708736896515,
      "eval_runtime": 6.4155,
      "eval_samples_per_second": 584.521,
      "eval_steps_per_second": 9.196,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.038916587829589844,
      "learning_rate": 2.2288955622288957e-05,
      "loss": 0.0299,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8736,
      "eval_loss": 0.49460554122924805,
      "eval_runtime": 5.9686,
      "eval_samples_per_second": 628.29,
      "eval_steps_per_second": 9.885,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.13790945708751678,
      "learning_rate": 1.1177844511177845e-05,
      "loss": 0.0145,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8869333333333334,
      "eval_loss": 0.47561874985694885,
      "eval_runtime": 6.4086,
      "eval_samples_per_second": 585.148,
      "eval_steps_per_second": 9.206,
      "step": 2664
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}