metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: resnet-101-finetuned-CivilEng11k
results: []
resnet-101-finetuned-CivilEng11k
This model is a fine-tuned version of microsoft/resnet-101 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5490
- Accuracy: 0.8542
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 320
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.81 | 3 | 1.0724 | 0.5729 |
| No log | 1.89 | 7 | 0.9717 | 0.6542 |
| 1.0293 | 2.97 | 11 | 0.8594 | 0.6678 |
| 1.0293 | 3.78 | 14 | 0.7830 | 0.7017 |
| 1.0293 | 4.86 | 18 | 0.6764 | 0.7593 |
| 0.78 | 5.95 | 22 | 0.6072 | 0.7831 |
| 0.78 | 6.76 | 25 | 0.5745 | 0.8339 |
| 0.78 | 7.84 | 29 | 0.5489 | 0.8508 |
| 0.6037 | 8.11 | 30 | 0.5490 | 0.8542 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.13.1+cpu
- Datasets 2.13.1
- Tokenizers 0.13.3