---
library_name: transformers
license: apache-2.0
base_model: aviola/checkpoints
tags:
- generated_from_trainer
datasets:
- temp_domino2
model-index:
- name: detrDominoTest
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# detrDominoTest

This model is a fine-tuned version of [aviola/checkpoints](https://huggingface.co/aviola/checkpoints) on the temp_domino2 dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.3907
- eval_map: 0.7678
- eval_map_50: 0.9735
- eval_map_75: 0.9265
- eval_map_small: 0.553
- eval_map_medium: 0.7932
- eval_map_large: 0.925
- eval_mar_1: 0.5446
- eval_mar_10: 0.8104
- eval_mar_100: 0.8114
- eval_mar_small: 0.5939
- eval_mar_medium: 0.8319
- eval_mar_large: 0.925
- eval_map_pip-1: 0.718
- eval_mar_100_pip-1: 0.7846
- eval_map_pip-10: 0.8274
- eval_mar_100_pip-10: 0.8619
- eval_map_pip-11: 0.798
- eval_mar_100_pip-11: 0.8231
- eval_map_pip-12: 0.7927
- eval_mar_100_pip-12: 0.8474
- eval_map_pip-2: 0.775
- eval_mar_100_pip-2: 0.795
- eval_map_pip-3: 0.8041
- eval_mar_100_pip-3: 0.8467
- eval_map_pip-4: 0.7733
- eval_mar_100_pip-4: 0.8
- eval_map_pip-5: 0.7476
- eval_mar_100_pip-5: 0.8097
- eval_map_pip-6: 0.6602
- eval_mar_100_pip-6: 0.7318
- eval_map_pip-7: 0.7531
- eval_mar_100_pip-7: 0.8115
- eval_map_pip-8: 0.7814
- eval_mar_100_pip-8: 0.8188
- eval_map_pip-9: 0.7831
- eval_mar_100_pip-9: 0.8067
- eval_runtime: 1.9309
- eval_samples_per_second: 15.019
- eval_steps_per_second: 2.072
- epoch: 1.0
- step: 39

## 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: 5e-05
- 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: cosine
- num_epochs: 100

### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1