metadata
library_name: transformers
license: apache-2.0
base_model: SenseTime/deformable-detr
tags:
- generated_from_trainer
model-index:
- name: deformable_detr
results: []
deformable_detr
This model is a fine-tuned version of SenseTime/deformable-detr on the None dataset. It achieves the following results on the evaluation set:
- eval_loss: 1.4893
- eval_runtime: 845.9936
- eval_samples_per_second: 7.67
- eval_steps_per_second: 3.836
- epoch: 1.0
- step: 723
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: 0.0002
- train_batch_size: 12
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 96
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 10
- mixed_precision_training: Native AMP
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2