Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0930

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0930
File size: 4,293 Bytes 
3e1806f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
 
{
  "best_metric": 0.5224,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0930/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "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": 0.0005,
      "loss": 3.297,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.16453333333333334,
      "eval_loss": 3.0360941886901855,
      "eval_runtime": 11.4409,
      "eval_samples_per_second": 327.77,
      "eval_steps_per_second": 5.157,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.7595,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2981333333333333,
      "eval_loss": 2.5701043605804443,
      "eval_runtime": 11.2817,
      "eval_samples_per_second": 332.397,
      "eval_steps_per_second": 5.23,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.383,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3586666666666667,
      "eval_loss": 2.308694839477539,
      "eval_runtime": 11.3341,
      "eval_samples_per_second": 330.861,
      "eval_steps_per_second": 5.206,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.486026763916016,
      "learning_rate": 0.0005,
      "loss": 2.0846,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3968,
      "eval_loss": 2.1531403064727783,
      "eval_runtime": 11.49,
      "eval_samples_per_second": 326.37,
      "eval_steps_per_second": 5.135,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.00288200378418,
      "learning_rate": 0.0005,
      "loss": 1.831,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.44266666666666665,
      "eval_loss": 1.9984676837921143,
      "eval_runtime": 11.2892,
      "eval_samples_per_second": 332.175,
      "eval_steps_per_second": 5.226,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 12.666269302368164,
      "learning_rate": 0.0005,
      "loss": 1.5906,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4746666666666667,
      "eval_loss": 1.9043924808502197,
      "eval_runtime": 11.3123,
      "eval_samples_per_second": 331.498,
      "eval_steps_per_second": 5.216,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 8.11579418182373,
      "learning_rate": 0.0005,
      "loss": 1.346,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5018666666666667,
      "eval_loss": 1.7887544631958008,
      "eval_runtime": 11.3385,
      "eval_samples_per_second": 330.732,
      "eval_steps_per_second": 5.204,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 8.022260665893555,
      "learning_rate": 0.0005,
      "loss": 1.1052,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.48933333333333334,
      "eval_loss": 1.8984284400939941,
      "eval_runtime": 11.4754,
      "eval_samples_per_second": 326.787,
      "eval_steps_per_second": 5.141,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 22.22198486328125,
      "learning_rate": 0.0005,
      "loss": 0.8566,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.5224,
      "eval_loss": 1.8789085149765015,
      "eval_runtime": 11.3745,
      "eval_samples_per_second": 329.686,
      "eval_steps_per_second": 5.187,
      "step": 2997
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}