lora_fine_tuned_boolq_googlemt_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: 0.6642
• Accuracy: 0.6217
• F1: 0.4767

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
0.6841	0.0424	50	0.6647	0.6217	0.4767
0.6685	0.0848	100	0.6632	0.6217	0.4767
0.6944	0.1272	150	0.6639	0.6217	0.4767
0.6581	0.1696	200	0.6632	0.6217	0.4767
0.6625	0.2120	250	0.6642	0.6217	0.4767
0.6532	0.2545	300	0.6661	0.6217	0.4767
0.6741	0.2969	350	0.6645	0.6217	0.4767
0.6852	0.3393	400	0.6642	0.6217	0.4767

Framework versions

• PEFT 0.11.1
• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1