loha_fine_tuned_boolq_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: 0.5904
• Accuracy: 0.8333
• F1: 0.8243

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
0.7131	4.1667	50	0.6457	0.7222	0.7325
0.676	8.3333	100	0.6157	0.7222	0.7325
0.6777	12.5	150	0.6047	0.7778	0.7778
0.687	16.6667	200	0.5982	0.7778	0.7778
0.669	20.8333	250	0.5940	0.8333	0.8243
0.6743	25.0	300	0.5911	0.8333	0.8243
0.6841	29.1667	350	0.5910	0.8333	0.8243
0.6639	33.3333	400	0.5904	0.8333	0.8243

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.40.1
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.19.1