Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0326

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0326
File size: 4,486 Bytes 
be07602
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8874666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0326/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": 6.625456809997559,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.8494,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7509333333333333,
      "eval_loss": 0.804374635219574,
      "eval_runtime": 6.621,
      "eval_samples_per_second": 566.383,
      "eval_steps_per_second": 8.911,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 8.833589107668211e-05,
      "loss": 0.5158,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8245333333333333,
      "eval_loss": 0.5573346614837646,
      "eval_runtime": 5.9641,
      "eval_samples_per_second": 628.763,
      "eval_steps_per_second": 9.893,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 14.56907844543457,
      "learning_rate": 7.504537663092833e-05,
      "loss": 0.2553,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5359163880348206,
      "eval_runtime": 5.7314,
      "eval_samples_per_second": 654.288,
      "eval_steps_per_second": 10.294,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6762597560882568,
      "learning_rate": 5.873402013309226e-05,
      "loss": 0.1255,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8576,
      "eval_loss": 0.49195241928100586,
      "eval_runtime": 5.7725,
      "eval_samples_per_second": 649.629,
      "eval_steps_per_second": 10.221,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2927664518356323,
      "learning_rate": 4.136921190679637e-05,
      "loss": 0.0583,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.48569682240486145,
      "eval_runtime": 5.6456,
      "eval_samples_per_second": 664.239,
      "eval_steps_per_second": 10.451,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.07220727950334549,
      "learning_rate": 2.5045404101407076e-05,
      "loss": 0.0227,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.45990613102912903,
      "eval_runtime": 5.6609,
      "eval_samples_per_second": 662.445,
      "eval_steps_per_second": 10.422,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.6883904933929443,
      "learning_rate": 1.1731488851999511e-05,
      "loss": 0.0069,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.4549057185649872,
      "eval_runtime": 5.9448,
      "eval_samples_per_second": 630.805,
      "eval_steps_per_second": 9.925,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.02105369232594967,
      "learning_rate": 3.033320830114261e-06,
      "loss": 0.0031,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8866666666666667,
      "eval_loss": 0.45643138885498047,
      "eval_runtime": 5.7115,
      "eval_samples_per_second": 656.574,
      "eval_steps_per_second": 10.33,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.06399612128734589,
      "learning_rate": 2.7470478758395702e-11,
      "loss": 0.0026,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.45565181970596313,
      "eval_runtime": 5.6515,
      "eval_samples_per_second": 663.537,
      "eval_steps_per_second": 10.44,
      "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
}