Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0477

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0477
File size: 4,465 Bytes 
336518e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8618666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0477/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": 0.00026676676676676677,
      "loss": 1.6962,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7392,
      "eval_loss": 0.8529876470565796,
      "eval_runtime": 6.0548,
      "eval_samples_per_second": 619.34,
      "eval_steps_per_second": 9.744,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8332898616790771,
      "learning_rate": 0.00023343343343343342,
      "loss": 0.617,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7610666666666667,
      "eval_loss": 0.7613883018493652,
      "eval_runtime": 5.9085,
      "eval_samples_per_second": 634.675,
      "eval_steps_per_second": 9.986,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.49308058619499207,
      "learning_rate": 0.00020010010010010007,
      "loss": 0.3346,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8093333333333333,
      "eval_loss": 0.6180067658424377,
      "eval_runtime": 5.6543,
      "eval_samples_per_second": 663.21,
      "eval_steps_per_second": 10.434,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.612032175064087,
      "learning_rate": 0.00016676676676676675,
      "loss": 0.1811,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8178666666666666,
      "eval_loss": 0.6305338740348816,
      "eval_runtime": 6.1587,
      "eval_samples_per_second": 608.895,
      "eval_steps_per_second": 9.58,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00013353353353353354,
      "loss": 0.0953,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8298666666666666,
      "eval_loss": 0.6424050331115723,
      "eval_runtime": 5.9798,
      "eval_samples_per_second": 627.108,
      "eval_steps_per_second": 9.867,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.010922795161604881,
      "learning_rate": 0.0001002002002002002,
      "loss": 0.0416,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.6422730088233948,
      "eval_runtime": 5.8664,
      "eval_samples_per_second": 639.238,
      "eval_steps_per_second": 10.057,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.026294806972146034,
      "learning_rate": 6.686686686686686e-05,
      "loss": 0.0138,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.856,
      "eval_loss": 0.6165120005607605,
      "eval_runtime": 6.7829,
      "eval_samples_per_second": 552.857,
      "eval_steps_per_second": 8.698,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.045803435146808624,
      "learning_rate": 3.3533533533533535e-05,
      "loss": 0.0024,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8602666666666666,
      "eval_loss": 0.6117628216743469,
      "eval_runtime": 5.6122,
      "eval_samples_per_second": 668.191,
      "eval_steps_per_second": 10.513,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.020099680870771408,
      "learning_rate": 2.002002002002002e-07,
      "loss": 0.0014,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8618666666666667,
      "eval_loss": 0.6024093627929688,
      "eval_runtime": 6.3705,
      "eval_samples_per_second": 588.653,
      "eval_steps_per_second": 9.261,
      "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
}