Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0106

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0106
File size: 3,906 Bytes 
65fafb8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9034666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0106/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": 5e-05,
      "loss": 1.8462,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8224,
      "eval_loss": 0.7731029987335205,
      "eval_runtime": 6.7808,
      "eval_samples_per_second": 553.03,
      "eval_steps_per_second": 8.701,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.14887046813965,
      "learning_rate": 5e-05,
      "loss": 0.5379,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8669333333333333,
      "eval_loss": 0.4905170798301697,
      "eval_runtime": 6.8024,
      "eval_samples_per_second": 551.272,
      "eval_steps_per_second": 8.673,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.527515172958374,
      "learning_rate": 5e-05,
      "loss": 0.3171,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.44772788882255554,
      "eval_runtime": 6.793,
      "eval_samples_per_second": 552.039,
      "eval_steps_per_second": 8.685,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.40494441986084,
      "learning_rate": 5e-05,
      "loss": 0.2103,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8893333333333333,
      "eval_loss": 0.40557587146759033,
      "eval_runtime": 6.8151,
      "eval_samples_per_second": 550.246,
      "eval_steps_per_second": 8.657,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2175290584564209,
      "learning_rate": 5e-05,
      "loss": 0.1536,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.88,
      "eval_loss": 0.40745142102241516,
      "eval_runtime": 7.0889,
      "eval_samples_per_second": 528.999,
      "eval_steps_per_second": 8.323,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.18534567952156067,
      "learning_rate": 5e-05,
      "loss": 0.1122,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.38797372579574585,
      "eval_runtime": 6.8599,
      "eval_samples_per_second": 546.652,
      "eval_steps_per_second": 8.601,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 25.028366088867188,
      "learning_rate": 5e-05,
      "loss": 0.0892,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.41365063190460205,
      "eval_runtime": 6.9902,
      "eval_samples_per_second": 536.465,
      "eval_steps_per_second": 8.44,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.03557448834180832,
      "learning_rate": 5e-05,
      "loss": 0.0723,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9034666666666666,
      "eval_loss": 0.38665488362312317,
      "eval_runtime": 7.2712,
      "eval_samples_per_second": 515.733,
      "eval_steps_per_second": 8.114,
      "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
}