Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0761

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0761
File size: 4,443 Bytes 
a6adf93
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8794666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0761/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": 4.850126564054637e-05,
      "loss": 1.8964,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7888,
      "eval_loss": 0.8514412045478821,
      "eval_runtime": 6.04,
      "eval_samples_per_second": 620.862,
      "eval_steps_per_second": 9.768,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 4.4184758936602036e-05,
      "loss": 0.5618,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8453333333333334,
      "eval_loss": 0.5358413457870483,
      "eval_runtime": 5.3634,
      "eval_samples_per_second": 699.189,
      "eval_steps_per_second": 11.001,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.854659080505371,
      "learning_rate": 3.7545362870758595e-05,
      "loss": 0.2679,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8509333333333333,
      "eval_loss": 0.49762168526649475,
      "eval_runtime": 5.4358,
      "eval_samples_per_second": 689.869,
      "eval_steps_per_second": 10.854,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9210184216499329,
      "learning_rate": 2.9392810892864702e-05,
      "loss": 0.1273,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8672,
      "eval_loss": 0.4746966063976288,
      "eval_runtime": 5.421,
      "eval_samples_per_second": 691.753,
      "eval_steps_per_second": 10.884,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.22152237594127655,
      "learning_rate": 2.0710421090307246e-05,
      "loss": 0.0584,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.4710146188735962,
      "eval_runtime": 5.4667,
      "eval_samples_per_second": 685.966,
      "eval_steps_per_second": 10.793,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1616952419281006,
      "learning_rate": 1.2545417811701016e-05,
      "loss": 0.0206,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.479625403881073,
      "eval_runtime": 5.5635,
      "eval_samples_per_second": 674.042,
      "eval_steps_per_second": 10.605,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.4418635070323944,
      "learning_rate": 5.882620955060414e-06,
      "loss": 0.0089,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.4796392023563385,
      "eval_runtime": 6.0878,
      "eval_samples_per_second": 615.982,
      "eval_steps_per_second": 9.691,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.40027204155921936,
      "learning_rate": 1.5256621537052152e-06,
      "loss": 0.0057,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8792,
      "eval_loss": 0.47914251685142517,
      "eval_runtime": 5.5408,
      "eval_samples_per_second": 676.796,
      "eval_steps_per_second": 10.648,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.06340394169092178,
      "learning_rate": 5.494094242330938e-11,
      "loss": 0.0049,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.48026591539382935,
      "eval_runtime": 5.8001,
      "eval_samples_per_second": 646.544,
      "eval_steps_per_second": 10.172,
      "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
}