bert-base-cased-squad-v1.1-pt_IBAMA_v0.1620

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 9.7849

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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	54	9.2114
No log	2.0	108	8.6424
No log	3.0	162	9.2190
No log	4.0	216	9.4396
No log	5.0	270	9.2036
No log	6.0	324	9.9266
No log	7.0	378	9.1863
No log	8.0	432	9.5205
No log	9.0	486	9.4914
0.1145	10.0	540	9.7393
0.1145	11.0	594	9.5494
0.1145	12.0	648	9.7259
0.1145	13.0	702	10.0733
0.1145	14.0	756	9.8568
0.1145	15.0	810	9.9302
0.1145	16.0	864	9.5032
0.1145	17.0	918	9.8845
0.1145	18.0	972	9.6405
0.0605	19.0	1026	9.7906
0.0605	20.0	1080	9.7849

Framework versions

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