image-quality-mobilenetv3

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0123

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 256
  • eval_batch_size: 256
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss
4.3424 1.0 36 3.0847
0.6173 2.0 72 0.4851
0.1393 3.0 108 0.0988
0.0575 4.0 144 0.0536
0.0388 5.0 180 0.0377
0.0324 6.0 216 0.0320
0.0291 7.0 252 0.0312
0.0255 8.0 288 0.0266
0.023 9.0 324 0.0232
0.0213 10.0 360 0.0214
0.0205 11.0 396 0.0209
0.0193 12.0 432 0.0198
0.0183 13.0 468 0.0191
0.0185 14.0 504 0.0179
0.0175 15.0 540 0.0171
0.0166 16.0 576 0.0186
0.0161 17.0 612 0.0167
0.0164 18.0 648 0.0163
0.0152 19.0 684 0.0160
0.0149 20.0 720 0.0156
0.0151 21.0 756 0.0159
0.0147 22.0 792 0.0153
0.0154 23.0 828 0.0162
0.0147 24.0 864 0.0150
0.0144 25.0 900 0.0147
0.0143 26.0 936 0.0144
0.0144 27.0 972 0.0139
0.0152 28.0 1008 0.0150
0.0129 29.0 1044 0.0134
0.0128 30.0 1080 0.0135
0.0126 31.0 1116 0.0141
0.0131 32.0 1152 0.0145
0.0133 33.0 1188 0.0131
0.0124 34.0 1224 0.0133
0.013 35.0 1260 0.0148
0.0121 36.0 1296 0.0129
0.0116 37.0 1332 0.0127
0.0124 38.0 1368 0.0129
0.0121 39.0 1404 0.0134
0.0121 40.0 1440 0.0128
0.0119 41.0 1476 0.0126
0.0116 42.0 1512 0.0125
0.0118 43.0 1548 0.0126
0.0114 44.0 1584 0.0127
0.0117 45.0 1620 0.0125
0.0116 46.0 1656 0.0127
0.0118 47.0 1692 0.0126
0.0116 48.0 1728 0.0123
0.0114 49.0 1764 0.0123
0.0113 50.0 1800 0.0123

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
11
Safetensors
Model size
4.23M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kilia/image-quality-mobilenetv3

Finetuned
(2)
this model