electraForCausalLM / README.md
Gan1108's picture
Update README.md
ad1eae2 verified
metadata
license: mit
base_model: lang-uk/electra-base-ukrainian-cased-generator
tags:
  - generated_from_trainer
model-index:
  - name: electraForCausalLM
    results: []
language:
  - uk
widget:
  - text: '0007347852 - 734785.0 - Підшипник кульковий закритий спеціальний '

electraForCausalLM

This model is a fine-tuned version of lang-uk/electra-base-ukrainian-cased-generator on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3302

Model description

The model is trained to generate a text description in Ukrainian of spare parts for agricultural machinery based on their name.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-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
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
1.7321 1.0 2354 1.5172
1.4763 2.0 4708 1.3670
1.4006 3.0 7062 1.3302

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2