---
library_name: transformers
license: apache-2.0
base_model: microsoft/beit-large-patch16-384
tags:
- image-regression
- human-movement
- vision
- generated_from_trainer
model-index:
- name: limbxy_pose
  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. -->

# limbxy_pose

This model is a fine-tuned version of [microsoft/beit-large-patch16-384](https://huggingface.co/microsoft/beit-large-patch16-384) on the c14kevincardenas/beta_caller_284_limbxy_pose dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1399
- Rmse: 0.3740

## 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: 64
- eval_batch_size: 64
- seed: 2014
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- num_epochs: 20.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rmse   |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2029        | 1.0   | 89   | 0.2039          | 0.4516 |
| 0.1535        | 2.0   | 178  | 0.1545          | 0.3931 |
| 0.1847        | 3.0   | 267  | 0.1640          | 0.4050 |
| 0.1582        | 4.0   | 356  | 0.1427          | 0.3777 |
| 0.1471        | 5.0   | 445  | 0.1427          | 0.3778 |
| 0.1553        | 6.0   | 534  | 0.1469          | 0.3833 |
| 0.1613        | 7.0   | 623  | 0.1430          | 0.3782 |
| 0.1471        | 8.0   | 712  | 0.1427          | 0.3778 |
| 0.1587        | 9.0   | 801  | 0.1417          | 0.3764 |
| 0.1504        | 10.0  | 890  | 0.1427          | 0.3777 |
| 0.1431        | 11.0  | 979  | 0.1429          | 0.3780 |
| 0.1455        | 12.0  | 1068 | 0.1442          | 0.3797 |
| 0.1515        | 13.0  | 1157 | 0.1431          | 0.3783 |
| 0.1407        | 14.0  | 1246 | 0.1443          | 0.3799 |
| 0.1436        | 15.0  | 1335 | 0.1419          | 0.3768 |
| 0.1425        | 16.0  | 1424 | 0.1399          | 0.3740 |
| 0.1411        | 17.0  | 1513 | 0.1401          | 0.3743 |
| 0.1401        | 18.0  | 1602 | 0.1408          | 0.3752 |
| 0.1426        | 19.0  | 1691 | 0.1406          | 0.3750 |
| 0.1388        | 20.0  | 1780 | 0.1400          | 0.3742 |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1