samitizerxu's picture
End of training
e08b2cd verified
metadata
license: other
base_model: nvidia/mit-b1
tags:
  - vision
  - image-segmentation
  - generated_from_trainer
datasets:
  - kelp_data
model-index:
  - name: segformer-b1-kelp-rgb-agg-imgaug-jan-22
    results: []

segformer-b1-kelp-rgb-agg-imgaug-jan-22

This model is a fine-tuned version of nvidia/mit-b1 on the samitizerxu/kelp_data dataset. It achieves the following results on the evaluation set:

  • eval_accuracy_kelp: nan
  • eval_iou_kelp: 0.0
  • eval_loss: 0.3223
  • eval_mean_iou: 0.0205
  • eval_mean_accuracy: 0.0410
  • eval_overall_accuracy: 0.0410
  • eval_runtime: 62.0057
  • eval_samples_per_second: 27.272
  • eval_steps_per_second: 3.419
  • epoch: 1.16
  • step: 570

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.2
  • num_epochs: 40

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0