Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0858

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0858
File size: 4,066 Bytes 
2b37e9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.5637333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0858/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": 0.0004810825448943271,
      "loss": 3.1061,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.25146666666666667,
      "eval_loss": 2.720893144607544,
      "eval_runtime": 12.3161,
      "eval_samples_per_second": 304.479,
      "eval_steps_per_second": 4.79,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.808862209320068,
      "learning_rate": 0.0004269850409335979,
      "loss": 2.4996,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.34746666666666665,
      "eval_loss": 2.3549532890319824,
      "eval_runtime": 12.2058,
      "eval_samples_per_second": 307.23,
      "eval_steps_per_second": 4.834,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003462153462094779,
      "loss": 2.0748,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3933333333333333,
      "eval_loss": 2.119504928588867,
      "eval_runtime": 12.0547,
      "eval_samples_per_second": 311.082,
      "eval_steps_per_second": 4.894,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.590587615966797,
      "learning_rate": 0.00025058963771413845,
      "loss": 1.7144,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.46266666666666667,
      "eval_loss": 1.8725024461746216,
      "eval_runtime": 12.1661,
      "eval_samples_per_second": 308.234,
      "eval_steps_per_second": 4.85,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.0893821716308594,
      "learning_rate": 0.00015487416222190068,
      "loss": 1.3423,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.49866666666666665,
      "eval_loss": 1.7233307361602783,
      "eval_runtime": 12.2196,
      "eval_samples_per_second": 306.884,
      "eval_steps_per_second": 4.828,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.208774566650391,
      "learning_rate": 7.36407332135117e-05,
      "loss": 0.9352,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5477333333333333,
      "eval_loss": 1.5967743396759033,
      "eval_runtime": 12.4383,
      "eval_samples_per_second": 301.487,
      "eval_steps_per_second": 4.743,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.025923728942871,
      "learning_rate": 1.9256403872631112e-05,
      "loss": 0.5701,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5624,
      "eval_loss": 1.5825021266937256,
      "eval_runtime": 12.4101,
      "eval_samples_per_second": 302.174,
      "eval_steps_per_second": 4.754,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.78461217880249,
      "learning_rate": 6.953462348691098e-10,
      "loss": 0.3929,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5637333333333333,
      "eval_loss": 1.5756717920303345,
      "eval_runtime": 12.397,
      "eval_samples_per_second": 302.492,
      "eval_steps_per_second": 4.759,
      "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
}