Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0437

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0437
File size: 3,902 Bytes 
ff595dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7584,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0437/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": 0.0003,
      "loss": 2.9403,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.37333333333333335,
      "eval_loss": 2.2324419021606445,
      "eval_runtime": 5.9446,
      "eval_samples_per_second": 630.823,
      "eval_steps_per_second": 9.925,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 1.6074,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6256,
      "eval_loss": 1.264017939567566,
      "eval_runtime": 5.9536,
      "eval_samples_per_second": 629.874,
      "eval_steps_per_second": 9.91,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.221931219100952,
      "learning_rate": 0.0003,
      "loss": 0.9111,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7026666666666667,
      "eval_loss": 0.9553343057632446,
      "eval_runtime": 6.183,
      "eval_samples_per_second": 606.503,
      "eval_steps_per_second": 9.542,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.3740243911743164,
      "learning_rate": 0.0003,
      "loss": 0.5896,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7472,
      "eval_loss": 0.8192077279090881,
      "eval_runtime": 6.2598,
      "eval_samples_per_second": 599.056,
      "eval_steps_per_second": 9.425,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.35036253929138184,
      "learning_rate": 0.0003,
      "loss": 0.4005,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7509333333333333,
      "eval_loss": 0.8488056659698486,
      "eval_runtime": 5.9597,
      "eval_samples_per_second": 629.227,
      "eval_steps_per_second": 9.9,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3262908458709717,
      "learning_rate": 0.0003,
      "loss": 0.2914,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7490666666666667,
      "eval_loss": 0.8962832093238831,
      "eval_runtime": 5.9293,
      "eval_samples_per_second": 632.456,
      "eval_steps_per_second": 9.951,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.3573453426361084,
      "learning_rate": 0.0003,
      "loss": 0.2237,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7533333333333333,
      "eval_loss": 0.9267802238464355,
      "eval_runtime": 5.9129,
      "eval_samples_per_second": 634.204,
      "eval_steps_per_second": 9.978,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 9.490854263305664,
      "learning_rate": 0.0003,
      "loss": 0.1791,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7584,
      "eval_loss": 0.9212382435798645,
      "eval_runtime": 5.8385,
      "eval_samples_per_second": 642.291,
      "eval_steps_per_second": 10.105,
      "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
}