metadata
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dog_emotion_v3_resnet
results: []
dog_emotion_v3_resnet
This model is a fine-tuned version of microsoft/resnet-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3063
- Accuracy: 0.5075
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: 5.5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 50 | 1.3721 | 0.3475 |
| No log | 2.0 | 100 | 1.3502 | 0.45 |
| No log | 3.0 | 150 | 1.3292 | 0.485 |
| No log | 4.0 | 200 | 1.3103 | 0.5025 |
| No log | 5.0 | 250 | 1.3063 | 0.5075 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3