Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0880

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0880
File size: 4,026 Bytes 
83c3cb3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8784,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0880/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": 4.46605110168457,
      "learning_rate": 0.000288581929876693,
      "loss": 2.2363,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6498666666666667,
      "eval_loss": 1.185250163078308,
      "eval_runtime": 5.7724,
      "eval_samples_per_second": 649.646,
      "eval_steps_per_second": 10.221,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.674740195274353,
      "learning_rate": 0.00025619102456015866,
      "loss": 0.7781,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7752,
      "eval_loss": 0.7510872483253479,
      "eval_runtime": 5.8162,
      "eval_samples_per_second": 644.75,
      "eval_steps_per_second": 10.144,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002077292077256867,
      "loss": 0.4329,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8152,
      "eval_loss": 0.6161290407180786,
      "eval_runtime": 5.8804,
      "eval_samples_per_second": 637.716,
      "eval_steps_per_second": 10.033,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.994841575622559,
      "learning_rate": 0.00015035378262848306,
      "loss": 0.2245,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8330666666666666,
      "eval_loss": 0.5581854581832886,
      "eval_runtime": 8.1012,
      "eval_samples_per_second": 462.895,
      "eval_steps_per_second": 7.283,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 9.308812260256249e-05,
      "loss": 0.0965,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8461333333333333,
      "eval_loss": 0.5367787480354309,
      "eval_runtime": 11.0243,
      "eval_samples_per_second": 340.157,
      "eval_steps_per_second": 5.352,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.041738130152225494,
      "learning_rate": 4.4309889303710674e-05,
      "loss": 0.0292,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.5073858499526978,
      "eval_runtime": 5.5058,
      "eval_samples_per_second": 681.098,
      "eval_steps_per_second": 10.716,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.016711849719285965,
      "learning_rate": 1.1622017275129708e-05,
      "loss": 0.0082,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.47788867354393005,
      "eval_runtime": 5.5127,
      "eval_samples_per_second": 680.253,
      "eval_steps_per_second": 10.703,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.007322981953620911,
      "learning_rate": 9.387168731500582e-10,
      "loss": 0.0037,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.47324422001838684,
      "eval_runtime": 5.5302,
      "eval_samples_per_second": 678.091,
      "eval_steps_per_second": 10.669,
      "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
}