lenatr99's picture
lora_fine_tuned_rte_croslo
bd2ccc9 verified
metadata
license: cc-by-4.0
library_name: peft
tags:
  - generated_from_trainer
base_model: EMBEDDIA/crosloengual-bert
metrics:
  - accuracy
  - f1
model-index:
  - name: lora_fine_tuned_rte_croslo
    results: []

lora_fine_tuned_rte_croslo

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

  • Loss: 0.6930
  • Accuracy: 0.5517
  • F1: 0.5539

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-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
  • training_steps: 400

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.7153 1.7241 50 0.6873 0.6207 0.6090
0.6965 3.4483 100 0.6882 0.5862 0.5789
0.7135 5.1724 150 0.6917 0.5862 0.5862
0.6938 6.8966 200 0.6943 0.5517 0.5539
0.6975 8.6207 250 0.6941 0.5517 0.5539
0.6994 10.3448 300 0.6943 0.5517 0.5539
0.6924 12.0690 350 0.6932 0.5517 0.5539
0.686 13.7931 400 0.6930 0.5517 0.5539

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1