Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0863

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0863
File size: 3,948 Bytes 
04bfbf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8690666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0863/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": 3e-05,
      "loss": 2.3085,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7274666666666667,
      "eval_loss": 1.1374921798706055,
      "eval_runtime": 5.8382,
      "eval_samples_per_second": 642.325,
      "eval_steps_per_second": 10.106,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.8198,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7914666666666667,
      "eval_loss": 0.7178482413291931,
      "eval_runtime": 6.9409,
      "eval_samples_per_second": 540.278,
      "eval_steps_per_second": 8.5,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.450586318969727,
      "learning_rate": 3e-05,
      "loss": 0.4784,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8397333333333333,
      "eval_loss": 0.5261227488517761,
      "eval_runtime": 5.944,
      "eval_samples_per_second": 630.888,
      "eval_steps_per_second": 9.926,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.727218747138977,
      "learning_rate": 3e-05,
      "loss": 0.318,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.47514140605926514,
      "eval_runtime": 6.4631,
      "eval_samples_per_second": 580.22,
      "eval_steps_per_second": 9.129,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.3591742515563965,
      "learning_rate": 3e-05,
      "loss": 0.2177,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.4634805917739868,
      "eval_runtime": 5.8435,
      "eval_samples_per_second": 641.735,
      "eval_steps_per_second": 10.097,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 38.02006530761719,
      "learning_rate": 3e-05,
      "loss": 0.1562,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8597333333333333,
      "eval_loss": 0.46424078941345215,
      "eval_runtime": 5.823,
      "eval_samples_per_second": 644.002,
      "eval_steps_per_second": 10.132,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.3365786075592041,
      "learning_rate": 3e-05,
      "loss": 0.1077,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.47450771927833557,
      "eval_runtime": 5.8701,
      "eval_samples_per_second": 638.828,
      "eval_steps_per_second": 10.051,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.23141619563102722,
      "learning_rate": 3e-05,
      "loss": 0.0794,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.4704905152320862,
      "eval_runtime": 5.8626,
      "eval_samples_per_second": 639.647,
      "eval_steps_per_second": 10.064,
      "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
}