Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0990

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0990
File size: 4,304 Bytes 
4b822ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8808,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0990/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": 7e-05,
      "loss": 1.5597,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8274666666666667,
      "eval_loss": 0.6503348350524902,
      "eval_runtime": 11.7142,
      "eval_samples_per_second": 320.124,
      "eval_steps_per_second": 5.037,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.2794623374938965,
      "learning_rate": 7e-05,
      "loss": 0.435,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.46115842461586,
      "eval_runtime": 11.7492,
      "eval_samples_per_second": 319.17,
      "eval_steps_per_second": 5.022,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.753475666046143,
      "learning_rate": 7e-05,
      "loss": 0.2215,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8530666666666666,
      "eval_loss": 0.5087929964065552,
      "eval_runtime": 12.4901,
      "eval_samples_per_second": 300.237,
      "eval_steps_per_second": 4.724,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 22.790523529052734,
      "learning_rate": 7e-05,
      "loss": 0.1261,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.5097166895866394,
      "eval_runtime": 11.2198,
      "eval_samples_per_second": 334.229,
      "eval_steps_per_second": 5.259,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.39854344725608826,
      "learning_rate": 7e-05,
      "loss": 0.0884,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.47259092330932617,
      "eval_runtime": 11.7384,
      "eval_samples_per_second": 319.464,
      "eval_steps_per_second": 5.026,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 7e-05,
      "loss": 0.0651,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.868,
      "eval_loss": 0.49679651856422424,
      "eval_runtime": 12.0136,
      "eval_samples_per_second": 312.147,
      "eval_steps_per_second": 4.911,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.054140541702508926,
      "learning_rate": 7e-05,
      "loss": 0.0477,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.5355271697044373,
      "eval_runtime": 11.8618,
      "eval_samples_per_second": 316.142,
      "eval_steps_per_second": 4.974,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0236927792429924,
      "learning_rate": 7e-05,
      "loss": 0.0447,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8746666666666667,
      "eval_loss": 0.511197030544281,
      "eval_runtime": 11.7577,
      "eval_samples_per_second": 318.941,
      "eval_steps_per_second": 5.018,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.012552314437925816,
      "learning_rate": 7e-05,
      "loss": 0.036,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8808,
      "eval_loss": 0.5288822054862976,
      "eval_runtime": 11.617,
      "eval_samples_per_second": 322.802,
      "eval_steps_per_second": 5.079,
      "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
}