Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0811

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0811
File size: 4,065 Bytes 
0a14b7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8949333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0811/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": 2.667667667667668e-05,
      "loss": 2.2925,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7592,
      "eval_loss": 1.1245934963226318,
      "eval_runtime": 5.7295,
      "eval_samples_per_second": 654.504,
      "eval_steps_per_second": 10.298,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.9691362380981445,
      "learning_rate": 2.3343343343343343e-05,
      "loss": 0.7131,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.6263790130615234,
      "eval_runtime": 5.7608,
      "eval_samples_per_second": 650.953,
      "eval_steps_per_second": 10.242,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 30.47370719909668,
      "learning_rate": 2.001001001001001e-05,
      "loss": 0.3407,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.4733610451221466,
      "eval_runtime": 5.8245,
      "eval_samples_per_second": 643.828,
      "eval_steps_per_second": 10.13,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3249468803405762,
      "learning_rate": 1.6676676676676678e-05,
      "loss": 0.1755,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.4297676980495453,
      "eval_runtime": 6.0938,
      "eval_samples_per_second": 615.379,
      "eval_steps_per_second": 9.682,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.33959072828292847,
      "learning_rate": 1.3343343343343344e-05,
      "loss": 0.0918,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.41033169627189636,
      "eval_runtime": 5.9562,
      "eval_samples_per_second": 629.6,
      "eval_steps_per_second": 9.906,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9662572145462036,
      "learning_rate": 1.001001001001001e-05,
      "loss": 0.0463,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8896,
      "eval_loss": 0.3936386704444885,
      "eval_runtime": 5.658,
      "eval_samples_per_second": 662.781,
      "eval_steps_per_second": 10.428,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.5572746396064758,
      "learning_rate": 6.676676676676677e-06,
      "loss": 0.0239,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8941333333333333,
      "eval_loss": 0.3942307233810425,
      "eval_runtime": 6.1894,
      "eval_samples_per_second": 605.872,
      "eval_steps_per_second": 9.532,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.41292035579681396,
      "learning_rate": 3.3433433433433436e-06,
      "loss": 0.0129,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8949333333333334,
      "eval_loss": 0.3954767882823944,
      "eval_runtime": 6.4666,
      "eval_samples_per_second": 579.9,
      "eval_steps_per_second": 9.124,
      "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
}