Edit model card

lora_fine_tuned_rte_XLMroberta

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6924
  • Accuracy: 0.5172
  • F1: 0.4944

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
0.6917 1.7241 50 0.7067 0.4138 0.2422
0.6974 3.4483 100 0.6924 0.5862 0.4333
0.697 5.1724 150 0.6968 0.4138 0.2422
0.6961 6.8966 200 0.6947 0.5172 0.4660
0.6952 8.6207 250 0.6947 0.4138 0.2951
0.6917 10.3448 300 0.6934 0.5517 0.5517
0.6907 12.0690 350 0.6923 0.4828 0.4479
0.6936 13.7931 400 0.6924 0.5172 0.4944

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_XLMroberta

Adapter
(20)
this model