Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0152

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0152
File size: 4,324 Bytes 
77d9a74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8805333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0152/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": 1.3351528644561768,
      "learning_rate": 7e-05,
      "loss": 1.5863,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7912,
      "eval_loss": 0.7460278868675232,
      "eval_runtime": 12.177,
      "eval_samples_per_second": 307.958,
      "eval_steps_per_second": 4.845,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.2484252452850342,
      "learning_rate": 7e-05,
      "loss": 0.4809,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5286544561386108,
      "eval_runtime": 12.3769,
      "eval_samples_per_second": 302.983,
      "eval_steps_per_second": 4.767,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 7e-05,
      "loss": 0.2902,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.4150317907333374,
      "eval_runtime": 12.5999,
      "eval_samples_per_second": 297.621,
      "eval_steps_per_second": 4.683,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.7005647420883179,
      "learning_rate": 7e-05,
      "loss": 0.1926,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.477612167596817,
      "eval_runtime": 12.245,
      "eval_samples_per_second": 306.247,
      "eval_steps_per_second": 4.818,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.096799373626709,
      "learning_rate": 7e-05,
      "loss": 0.1268,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8722666666666666,
      "eval_loss": 0.4646342992782593,
      "eval_runtime": 12.7381,
      "eval_samples_per_second": 294.393,
      "eval_steps_per_second": 4.632,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.37583065032958984,
      "learning_rate": 7e-05,
      "loss": 0.0984,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8733333333333333,
      "eval_loss": 0.47896429896354675,
      "eval_runtime": 14.7064,
      "eval_samples_per_second": 254.992,
      "eval_steps_per_second": 4.012,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.942385673522949,
      "learning_rate": 7e-05,
      "loss": 0.0736,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.508396327495575,
      "eval_runtime": 15.7505,
      "eval_samples_per_second": 238.087,
      "eval_steps_per_second": 3.746,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.0564889907836914,
      "learning_rate": 7e-05,
      "loss": 0.0645,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.5170808434486389,
      "eval_runtime": 12.2503,
      "eval_samples_per_second": 306.115,
      "eval_steps_per_second": 4.816,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.05687430500984192,
      "learning_rate": 7e-05,
      "loss": 0.053,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.5057439208030701,
      "eval_runtime": 12.5334,
      "eval_samples_per_second": 299.199,
      "eval_steps_per_second": 4.707,
      "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
}