Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0212

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0212
File size: 4,054 Bytes 
4b46de2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9074666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0212/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": 9.702037987560858e-05,
      "loss": 1.9967,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7784,
      "eval_loss": 0.7603841423988342,
      "eval_runtime": 8.2244,
      "eval_samples_per_second": 455.958,
      "eval_steps_per_second": 7.174,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2410590648651123,
      "learning_rate": 8.836951787320407e-05,
      "loss": 0.5641,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8237333333333333,
      "eval_loss": 0.5641454458236694,
      "eval_runtime": 7.7711,
      "eval_samples_per_second": 482.559,
      "eval_steps_per_second": 7.592,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.1315739154815674,
      "learning_rate": 7.509072574151719e-05,
      "loss": 0.332,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8634666666666667,
      "eval_loss": 0.4657822251319885,
      "eval_runtime": 7.6114,
      "eval_samples_per_second": 492.68,
      "eval_steps_per_second": 7.751,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.684788465499878,
      "learning_rate": 5.8785621785729404e-05,
      "loss": 0.2039,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.4455465078353882,
      "eval_runtime": 7.4468,
      "eval_samples_per_second": 503.574,
      "eval_steps_per_second": 7.923,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4212166965007782,
      "learning_rate": 4.142084218061449e-05,
      "loss": 0.1254,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8869333333333334,
      "eval_loss": 0.37117311358451843,
      "eval_runtime": 7.6013,
      "eval_samples_per_second": 493.334,
      "eval_steps_per_second": 7.762,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 2.5136294516063797e-05,
      "loss": 0.0689,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8922666666666667,
      "eval_loss": 0.36527955532073975,
      "eval_runtime": 7.6325,
      "eval_samples_per_second": 491.322,
      "eval_steps_per_second": 7.73,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.05110235884785652,
      "learning_rate": 1.1799036981326533e-05,
      "loss": 0.0307,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9032,
      "eval_loss": 0.352810263633728,
      "eval_runtime": 7.5577,
      "eval_samples_per_second": 496.186,
      "eval_steps_per_second": 7.807,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.11318311840295792,
      "learning_rate": 3.0693793728105435e-06,
      "loss": 0.0157,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9074666666666666,
      "eval_loss": 0.3576520085334778,
      "eval_runtime": 7.6238,
      "eval_samples_per_second": 491.879,
      "eval_steps_per_second": 7.739,
      "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
}