Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0075

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0075
File size: 4,428 Bytes 
dc2bac2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.9173333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0075/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": 9.700253128109275e-05,
      "loss": 1.5049,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8056,
      "eval_loss": 0.6911031007766724,
      "eval_runtime": 6.4141,
      "eval_samples_per_second": 584.654,
      "eval_steps_per_second": 9.199,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 8.836951787320407e-05,
      "loss": 0.4668,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.5149933099746704,
      "eval_runtime": 6.549,
      "eval_samples_per_second": 572.608,
      "eval_steps_per_second": 9.009,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 7.513604728193609e-05,
      "loss": 0.2651,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8546666666666667,
      "eval_loss": 0.45474764704704285,
      "eval_runtime": 6.641,
      "eval_samples_per_second": 564.676,
      "eval_steps_per_second": 8.884,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.25342801213264465,
      "learning_rate": 5.8837213784557087e-05,
      "loss": 0.1535,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8938666666666667,
      "eval_loss": 0.3672282099723816,
      "eval_runtime": 6.5317,
      "eval_samples_per_second": 574.127,
      "eval_steps_per_second": 9.033,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.0804781913757324,
      "learning_rate": 4.147248188137552e-05,
      "loss": 0.0841,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.3797927796840668,
      "eval_runtime": 8.4587,
      "eval_samples_per_second": 443.329,
      "eval_steps_per_second": 6.975,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.09423605352640152,
      "learning_rate": 2.5136294516063797e-05,
      "loss": 0.0371,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9101333333333333,
      "eval_loss": 0.3468913435935974,
      "eval_runtime": 6.4811,
      "eval_samples_per_second": 578.606,
      "eval_steps_per_second": 9.103,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.018107257783412933,
      "learning_rate": 1.1799036981326533e-05,
      "loss": 0.0173,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9144,
      "eval_loss": 0.3314496874809265,
      "eval_runtime": 6.6133,
      "eval_samples_per_second": 567.039,
      "eval_steps_per_second": 8.921,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.057890769094228745,
      "learning_rate": 3.0693793728105435e-06,
      "loss": 0.0072,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.916,
      "eval_loss": 0.3191704750061035,
      "eval_runtime": 6.4105,
      "eval_samples_per_second": 584.978,
      "eval_steps_per_second": 9.204,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.30312874913215637,
      "learning_rate": 2.472341277037771e-10,
      "loss": 0.005,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9173333333333333,
      "eval_loss": 0.31843462586402893,
      "eval_runtime": 6.6975,
      "eval_samples_per_second": 559.912,
      "eval_steps_per_second": 8.809,
      "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
}