twin_matcher_beta / README.md
SaladSlayer00's picture
Training in progress epoch 34
4e1a31b
metadata
license: apache-2.0
base_model: microsoft/resnet-50
tags:
  - generated_from_keras_callback
model-index:
  - name: SaladSlayer00/twin_matcher_beta
    results: []

SaladSlayer00/twin_matcher_beta

This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.0286
  • Validation Loss: 1.1866
  • Validation Accuracy: 0.7159
  • Epoch: 34

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:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Validation Accuracy Epoch
7.0814 4.8848 0.0133 0
4.6679 4.5568 0.0666 1
4.3536 4.1337 0.1221 2
3.8915 3.6650 0.2053 3
3.4256 3.2568 0.2597 4
3.0033 2.8885 0.3185 5
2.6252 2.5913 0.3973 6
2.2829 2.3391 0.4406 7
1.9821 2.1352 0.4928 8
1.7076 1.9428 0.5250 9
1.4693 1.8008 0.5627 10
1.2464 1.6763 0.5949 11
1.0552 1.5872 0.6093 12
0.9105 1.4840 0.6238 13
0.7595 1.4117 0.6426 14
0.6390 1.3601 0.6582 15
0.5328 1.3283 0.6548 16
0.4539 1.2958 0.6681 17
0.3655 1.2470 0.6715 18
0.3183 1.2389 0.6770 19
0.2597 1.2309 0.6792 20
0.2269 1.2193 0.6881 21
0.1750 1.2206 0.6781 22
0.1553 1.1853 0.6970 23
0.1313 1.1949 0.6781 24
0.1058 1.1935 0.6870 25
0.0903 1.2042 0.6859 26
0.0762 1.1950 0.6948 27
0.0654 1.1798 0.7037 28
0.0588 1.1955 0.6959 29
0.0488 1.1788 0.7048 30
0.0444 1.1845 0.7037 31
0.0374 1.1969 0.7026 32
0.0327 1.1907 0.7048 33
0.0286 1.1866 0.7159 34

Framework versions

  • Transformers 4.35.2
  • TensorFlow 2.15.0
  • Datasets 2.16.1
  • Tokenizers 0.15.0