mbert-loraxs-qa-LTr64-qkvd-ABohneLT-ABfr

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: 1.8400
• Exact Match: 57.52
• F1: 72.5509

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: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	F1
0.6300	1.0	1268	2.2646	56.8	72.0038
0.5329	2.0	2536	2.1893	58.32	72.5939
0.5866	3.0	3804	2.0928	57.52	72.2476
0.6509	4.0	5072	1.9853	57.76	72.4135
0.6980	5.0	6340	1.9111	57.2	72.1918
0.7529	6.0	7608	1.8505	57.76	72.7166
0.7801	7.0	8876	1.8400	57.52	72.5509

Framework versions

• PEFT 0.19.1
• Transformers 5.9.0
• Pytorch 2.11.0+cu128
• Datasets 4.8.5
• Tokenizers 0.22.2