bert-base-squad-v1.1-pt-IBAMA_v0.2.31071219

This model is a fine-tuned version of pierreguillou/bert-base-cased-squad-v1.1-portuguese on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0130

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	5	5.3704
No log	2.0	10	3.3652
No log	3.0	15	2.9078
No log	4.0	20	2.5955
No log	5.0	25	2.4333
No log	6.0	30	2.3101
No log	7.0	35	2.1799
No log	8.0	40	2.0779
No log	9.0	45	2.0280
No log	10.0	50	2.0130

Evaluation

{'exact_match': 5.0, 'f1': 46.51551708568315}

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1