fia24's picture
Final One
d03459c
metadata
base_model: csebuetnlp/banglat5
tags:
  - generated_from_trainer
model-index:
  - name: banel_with_pos_banglat5
    results: []

banel_with_pos_banglat5

This model is a fine-tuned version of csebuetnlp/banglat5 on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.2969
  • eval_Val Accuracy: 0.915
  • eval_gen_len: 2.2803
  • eval_runtime: 18.9292
  • eval_samples_per_second: 106.291
  • eval_steps_per_second: 3.328
  • epoch: 14.0
  • step: 1274

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: 0.0003
  • train_batch_size: 200
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 360

Framework versions

  • Transformers 4.34.1
  • Pytorch 1.13.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1