aguxez
/

snap-dumbbell-dfine-small-v87-corrected

Object Detection

Generated from Trainer

Model card Files Files and versions

snap-dumbbell-dfine-small-v87-corrected

This model is a fine-tuned version of aguxez/snap-dumbbell-dfine-small-v31-e4-replay-adapt on the aguxez/snap-equipment-youtube-v73-train-gt25-motion-corrected dataset.

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: 2e-06
train_batch_size: 4
eval_batch_size: 8
seed: 7
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: linear
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 5.14.1
Pytorch 2.13.0+cu130
Datasets 5.0.1
Tokenizers 0.22.2

Downloads last month: 24

Safetensors

Model size

10.2M params

Tensor type

F32

·

Model tree for aguxez/snap-dumbbell-dfine-small-v87-corrected

Base model

aguxez/snap-dumbbell-dfine-small-v31-e4-replay-adapt

Finetuned

(1)

this model