Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0692

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0692
File size: 4,022 Bytes 
83a7585
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.5664,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0692/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": 0.0004376876876876877,
      "loss": 3.167,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22693333333333332,
      "eval_loss": 2.8272547721862793,
      "eval_runtime": 13.4622,
      "eval_samples_per_second": 278.557,
      "eval_steps_per_second": 4.383,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00037537537537537537,
      "loss": 2.5912,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3506666666666667,
      "eval_loss": 2.371886968612671,
      "eval_runtime": 13.1294,
      "eval_samples_per_second": 285.618,
      "eval_steps_per_second": 4.494,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003130630630630631,
      "loss": 2.2037,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.40373333333333333,
      "eval_loss": 2.144225835800171,
      "eval_runtime": 13.3382,
      "eval_samples_per_second": 281.148,
      "eval_steps_per_second": 4.423,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.300422668457031,
      "learning_rate": 0.0002505630630630631,
      "loss": 1.8599,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4570666666666667,
      "eval_loss": 1.9323371648788452,
      "eval_runtime": 13.1465,
      "eval_samples_per_second": 285.246,
      "eval_steps_per_second": 4.488,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 19.085859298706055,
      "learning_rate": 0.00018806306306306305,
      "loss": 1.5391,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4896,
      "eval_loss": 1.8349400758743286,
      "eval_runtime": 13.0101,
      "eval_samples_per_second": 288.237,
      "eval_steps_per_second": 4.535,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 25.010496139526367,
      "learning_rate": 0.00012556306306306305,
      "loss": 1.1892,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5256,
      "eval_loss": 1.669935703277588,
      "eval_runtime": 13.0616,
      "eval_samples_per_second": 287.101,
      "eval_steps_per_second": 4.517,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.268948793411255,
      "learning_rate": 6.306306306306306e-05,
      "loss": 0.7904,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5506666666666666,
      "eval_loss": 1.6074273586273193,
      "eval_runtime": 12.884,
      "eval_samples_per_second": 291.058,
      "eval_steps_per_second": 4.579,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 25.087064743041992,
      "learning_rate": 5.630630630630631e-07,
      "loss": 0.4605,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5664,
      "eval_loss": 1.5900788307189941,
      "eval_runtime": 13.3092,
      "eval_samples_per_second": 281.761,
      "eval_steps_per_second": 4.433,
      "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
}