metadata
license: apache-2.0
base_model: microsoft/conditional-detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: conditional-detr-resnet-50_finetuned_CSGO
results: []
conditional-detr-resnet-50_finetuned_CSGO
This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6509
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7831 | 1.0 | 222 | 1.7830 |
| 1.191 | 2.0 | 444 | 1.1566 |
| 1.0365 | 3.0 | 666 | 1.0696 |
| 0.975 | 4.0 | 888 | 1.0674 |
| 0.9028 | 5.0 | 1110 | 0.9627 |
| 0.7875 | 6.0 | 1332 | 0.8937 |
| 0.6364 | 7.0 | 1554 | 0.7561 |
| 0.6012 | 8.0 | 1776 | 0.7053 |
| 0.5471 | 9.0 | 1998 | 0.6739 |
| 0.4852 | 10.0 | 2220 | 0.6509 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2