Edit model card

lora_fine_tuned_rte_sloberta

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

  • Loss: 0.6917
  • 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
0.6987 1.7241 50 0.6974 0.4483 0.3134
0.6918 3.4483 100 0.6891 0.5862 0.4333
0.694 5.1724 150 0.6964 0.3793 0.2764
0.6919 6.8966 200 0.6971 0.3793 0.2764
0.6904 8.6207 250 0.6930 0.4483 0.4443
0.6936 10.3448 300 0.6923 0.4828 0.4828
0.6901 12.0690 350 0.6913 0.6552 0.6491
0.6874 13.7931 400 0.6917 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
Downloads last month
0
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for lenatr99/lora_fine_tuned_rte_sloberta

Base model

EMBEDDIA/sloberta
Adapter
(17)
this model