Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0434

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0434
File size: 4,272 Bytes 
7d65f97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8082666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0434/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": 0.0003,
      "loss": 1.697,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7136,
      "eval_loss": 0.9402545690536499,
      "eval_runtime": 6.615,
      "eval_samples_per_second": 566.892,
      "eval_steps_per_second": 8.919,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.779387474060059,
      "learning_rate": 0.0003,
      "loss": 0.6648,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7653333333333333,
      "eval_loss": 0.7926506400108337,
      "eval_runtime": 6.7185,
      "eval_samples_per_second": 558.162,
      "eval_steps_per_second": 8.782,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.4267,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7802666666666667,
      "eval_loss": 0.727263867855072,
      "eval_runtime": 6.5782,
      "eval_samples_per_second": 570.067,
      "eval_steps_per_second": 8.969,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.959943175315857,
      "learning_rate": 0.0003,
      "loss": 0.292,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7813333333333333,
      "eval_loss": 0.7427392601966858,
      "eval_runtime": 6.483,
      "eval_samples_per_second": 578.432,
      "eval_steps_per_second": 9.101,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.834916591644287,
      "learning_rate": 0.0003,
      "loss": 0.2181,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.792,
      "eval_loss": 0.7447192668914795,
      "eval_runtime": 6.9565,
      "eval_samples_per_second": 539.061,
      "eval_steps_per_second": 8.481,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1746765375137329,
      "learning_rate": 0.0003,
      "loss": 0.1791,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7856,
      "eval_loss": 0.828454315662384,
      "eval_runtime": 6.9675,
      "eval_samples_per_second": 538.213,
      "eval_steps_per_second": 8.468,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 24.440576553344727,
      "learning_rate": 0.0003,
      "loss": 0.1512,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7872,
      "eval_loss": 0.865959644317627,
      "eval_runtime": 6.9947,
      "eval_samples_per_second": 536.121,
      "eval_steps_per_second": 8.435,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.09884683787822723,
      "learning_rate": 0.0003,
      "loss": 0.1289,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7896,
      "eval_loss": 0.8322427272796631,
      "eval_runtime": 6.3758,
      "eval_samples_per_second": 588.165,
      "eval_steps_per_second": 9.254,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 11.620436668395996,
      "learning_rate": 0.0003,
      "loss": 0.1196,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8082666666666667,
      "eval_loss": 0.7741094827651978,
      "eval_runtime": 6.5814,
      "eval_samples_per_second": 569.786,
      "eval_steps_per_second": 8.965,
      "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
}