Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0399

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0399
File size: 4,349 Bytes 
f8ffad4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7930666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0399/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": 4.108035564422607,
      "learning_rate": 0.0003,
      "loss": 1.8467,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6957333333333333,
      "eval_loss": 0.9857635498046875,
      "eval_runtime": 5.7486,
      "eval_samples_per_second": 652.337,
      "eval_steps_per_second": 10.263,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 0.7187,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7898666666666667,
      "eval_loss": 0.6947962045669556,
      "eval_runtime": 5.7935,
      "eval_samples_per_second": 647.276,
      "eval_steps_per_second": 10.184,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.667613983154297,
      "learning_rate": 0.0003,
      "loss": 0.431,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7885333333333333,
      "eval_loss": 0.6893866658210754,
      "eval_runtime": 6.1522,
      "eval_samples_per_second": 609.539,
      "eval_steps_per_second": 9.59,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 17.746402740478516,
      "learning_rate": 0.0003,
      "loss": 0.299,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7549333333333333,
      "eval_loss": 0.8416933417320251,
      "eval_runtime": 5.7497,
      "eval_samples_per_second": 652.204,
      "eval_steps_per_second": 10.261,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4448702335357666,
      "learning_rate": 0.0003,
      "loss": 0.228,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7858666666666667,
      "eval_loss": 0.7561094760894775,
      "eval_runtime": 5.6552,
      "eval_samples_per_second": 663.109,
      "eval_steps_per_second": 10.433,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.781618595123291,
      "learning_rate": 0.0003,
      "loss": 0.1924,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7909333333333334,
      "eval_loss": 0.7749009728431702,
      "eval_runtime": 5.7554,
      "eval_samples_per_second": 651.563,
      "eval_steps_per_second": 10.251,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 33.57717514038086,
      "learning_rate": 0.0003,
      "loss": 0.1637,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7850666666666667,
      "eval_loss": 0.8349209427833557,
      "eval_runtime": 6.1206,
      "eval_samples_per_second": 612.683,
      "eval_steps_per_second": 9.64,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.02094506472349167,
      "learning_rate": 0.0003,
      "loss": 0.1418,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7682666666666667,
      "eval_loss": 0.9396815896034241,
      "eval_runtime": 5.9164,
      "eval_samples_per_second": 633.835,
      "eval_steps_per_second": 9.972,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.03026556596159935,
      "learning_rate": 0.0003,
      "loss": 0.1295,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7930666666666667,
      "eval_loss": 0.8031014204025269,
      "eval_runtime": 5.9717,
      "eval_samples_per_second": 627.967,
      "eval_steps_per_second": 9.88,
      "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
}