mbert-loraxs-qa-r64-qkvd – AI Model by NastasiaM | AlphaNeural AI

You can deploy this model and start earning money today!

NastasiaM/
mbert-loraxs-qa-r64-qkvd

like

0

google-bert/bert-base-multilingual-cased

Views

No views yet

mbert-loraxs-qa-r64-qkvd

This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2882
Exact Match: 61.2
F1: 75.3705

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	F1
2.2315	1.0	1268	1.5361	54.72	68.1032
1.5011	2.0	2536	1.3413	58.8	73.0714
1.3040	3.0	3804	1.3030	60.24	74.3986
1.1689	4.0	5072	1.2922	61.2	74.9955
1.0839	5.0	6340	1.2882	61.2	75.3705

Framework versions

PEFT 0.19.1
Transformers 5.9.0
Pytorch 2.10.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2