Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0985

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0985
File size: 4,060 Bytes 
fe940ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9045333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0985/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": 7.987009048461914,
      "learning_rate": 7.875e-05,
      "loss": 1.5869,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7973333333333333,
      "eval_loss": 0.7425077557563782,
      "eval_runtime": 6.3951,
      "eval_samples_per_second": 586.389,
      "eval_steps_per_second": 9.226,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 6.753378378378378e-05,
      "loss": 0.5463,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8357333333333333,
      "eval_loss": 0.5471010804176331,
      "eval_runtime": 7.3226,
      "eval_samples_per_second": 512.114,
      "eval_steps_per_second": 8.057,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 5.6317567567567566e-05,
      "loss": 0.3274,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.46856415271759033,
      "eval_runtime": 7.3889,
      "eval_samples_per_second": 507.518,
      "eval_steps_per_second": 7.985,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12709756195545197,
      "learning_rate": 4.5067567567567564e-05,
      "loss": 0.2058,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8722666666666666,
      "eval_loss": 0.4306087791919708,
      "eval_runtime": 6.3053,
      "eval_samples_per_second": 594.735,
      "eval_steps_per_second": 9.357,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.15731993317604065,
      "learning_rate": 3.381756756756757e-05,
      "loss": 0.1286,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8845333333333333,
      "eval_loss": 0.39427611231803894,
      "eval_runtime": 6.2455,
      "eval_samples_per_second": 600.433,
      "eval_steps_per_second": 9.447,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07489936798810959,
      "learning_rate": 2.256756756756757e-05,
      "loss": 0.0734,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8885333333333333,
      "eval_loss": 0.39494895935058594,
      "eval_runtime": 6.4559,
      "eval_samples_per_second": 580.868,
      "eval_steps_per_second": 9.139,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.040048036724328995,
      "learning_rate": 1.1317567567567568e-05,
      "loss": 0.0394,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.38354986906051636,
      "eval_runtime": 6.5857,
      "eval_samples_per_second": 569.416,
      "eval_steps_per_second": 8.959,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.2212297916412354,
      "learning_rate": 6.756756756756757e-08,
      "loss": 0.0191,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9045333333333333,
      "eval_loss": 0.3618837296962738,
      "eval_runtime": 7.0496,
      "eval_samples_per_second": 531.947,
      "eval_steps_per_second": 8.369,
      "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
}