twin_matcher / README.md
SaladSlayer00's picture
Training in progress epoch 8
29cbcd6
---
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_keras_callback
model-index:
- name: SaladSlayer00/twin_matcher
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# SaladSlayer00/twin_matcher
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0494
- Validation Loss: 0.9150
- Validation Accuracy: 0.7791
- Epoch: 8
## 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': 0.0005, '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 |
|:----------:|:---------------:|:-------------------:|:-----:|
| 4.3094 | 2.8494 | 0.2653 | 0 |
| 1.9389 | 1.6614 | 0.5538 | 1 |
| 0.8892 | 1.1064 | 0.7059 | 2 |
| 0.4021 | 0.9831 | 0.7336 | 3 |
| 0.2010 | 0.8325 | 0.7814 | 4 |
| 0.1096 | 0.8393 | 0.7758 | 5 |
| 0.0681 | 0.8437 | 0.7880 | 6 |
| 0.0543 | 0.8610 | 0.7658 | 7 |
| 0.0494 | 0.9150 | 0.7791 | 8 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0