Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0573

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0573
File size: 4,301 Bytes 
48b1215
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.49466666666666664,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0573/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": 3.3042,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.20693333333333333,
      "eval_loss": 2.9039478302001953,
      "eval_runtime": 13.5222,
      "eval_samples_per_second": 277.321,
      "eval_steps_per_second": 4.363,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.7659,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3024,
      "eval_loss": 2.5815348625183105,
      "eval_runtime": 14.1062,
      "eval_samples_per_second": 265.84,
      "eval_steps_per_second": 4.183,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.193587303161621,
      "learning_rate": 0.0005,
      "loss": 2.4387,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3464,
      "eval_loss": 2.3880178928375244,
      "eval_runtime": 13.4731,
      "eval_samples_per_second": 278.333,
      "eval_steps_per_second": 4.379,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.994436264038086,
      "learning_rate": 0.0005,
      "loss": 2.1973,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.38613333333333333,
      "eval_loss": 2.1862568855285645,
      "eval_runtime": 13.649,
      "eval_samples_per_second": 274.746,
      "eval_steps_per_second": 4.323,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 16.781517028808594,
      "learning_rate": 0.0005,
      "loss": 1.9806,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4205333333333333,
      "eval_loss": 2.1110012531280518,
      "eval_runtime": 13.5487,
      "eval_samples_per_second": 276.779,
      "eval_steps_per_second": 4.355,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.784,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4464,
      "eval_loss": 1.987918496131897,
      "eval_runtime": 13.6396,
      "eval_samples_per_second": 274.935,
      "eval_steps_per_second": 4.326,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 12.475168228149414,
      "learning_rate": 0.0005,
      "loss": 1.6074,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4514666666666667,
      "eval_loss": 1.9620099067687988,
      "eval_runtime": 13.5201,
      "eval_samples_per_second": 277.365,
      "eval_steps_per_second": 4.364,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 11.580961227416992,
      "learning_rate": 0.0005,
      "loss": 1.4488,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.47226666666666667,
      "eval_loss": 1.936447024345398,
      "eval_runtime": 13.4381,
      "eval_samples_per_second": 279.058,
      "eval_steps_per_second": 4.391,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 15.137045860290527,
      "learning_rate": 0.0005,
      "loss": 1.2537,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.49466666666666664,
      "eval_loss": 1.87782621383667,
      "eval_runtime": 13.3775,
      "eval_samples_per_second": 280.321,
      "eval_steps_per_second": 4.41,
      "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
}