squad_a_r_train5_epoch_20

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0008
• Accuracy: 0.9994

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: 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6038	1.0	1188	0.5918	0.6938
0.5954	2.0	2376	0.6000	0.6957
0.5713	3.0	3564	0.5453	0.7342
0.5346	4.0	4752	0.4763	0.7841
0.4804	5.0	5940	0.3846	0.8298
0.4057	6.0	7128	0.2845	0.8835
0.3303	7.0	8316	0.1906	0.9259
0.2739	8.0	9504	0.1240	0.9564
0.2121	9.0	10692	0.0994	0.9714
0.1821	10.0	11880	0.0958	0.9756
0.1639	11.0	13068	0.0596	0.9853
0.1361	12.0	14256	0.0407	0.9895
0.1116	13.0	15444	0.0318	0.9924
0.0872	14.0	16632	0.0216	0.9954
0.072	15.0	17820	0.0125	0.9975
0.0648	16.0	19008	0.0167	0.9960
0.0537	17.0	20196	0.0126	0.9979
0.0404	18.0	21384	0.0045	0.9992
0.027	19.0	22572	0.0033	0.9987
0.0274	20.0	23760	0.0008	0.9994

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.0