correll's picture
End of training
e88ec46
metadata
license: other
base_model: nvidia/mit-b0
tags:
  - generated_from_trainer
model-index:
  - name: segformer-webots-grasp
    results: []

segformer-webots-grasp

This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 2.6628
  • eval_mean_iou: 0.8546
  • eval_mean_accuracy: 0.8633
  • eval_overall_accuracy: 0.8633
  • eval_per_category_iou: [0.8545649439735425, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
  • eval_per_category_accuracy: [0.8632884477610067, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
  • eval_runtime: 53.0339
  • eval_samples_per_second: 0.396
  • eval_steps_per_second: 0.207
  • epoch: 2.6
  • step: 104

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: 6e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0