lora_fine_tuned_copa_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: 0.6931
  • Accuracy: 0.51
  • F1: 0.5110

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: 0.003
  • 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
0.6977 1.0 50 0.6931 0.53 0.5242
0.6925 2.0 100 0.6931 0.45 0.4514
0.695 3.0 150 0.6931 0.61 0.6085
0.6982 4.0 200 0.6931 0.44 0.4200
0.699 5.0 250 0.6931 0.63 0.6285
0.6962 6.0 300 0.6931 0.51 0.5062
0.6918 7.0 350 0.6931 0.39 0.3893
0.6983 8.0 400 0.6931 0.51 0.5110

Framework versions

  • PEFT 0.10.1.dev0
  • Transformers 4.40.1
  • Pytorch 2.1.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
13
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for anzeo/lora_fine_tuned_copa_sloberta

Base model

EMBEDDIA/sloberta
Adapter
(17)
this model