mobilebert_sa_GLUE_Experiment_data_aug_mrpc_256

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Accuracy: 1.0
• F1: 1.0
• Combined Score: 1.0

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: 128
• eval_batch_size: 128
• seed: 10
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
0.1854	1.0	1959	0.0199	0.9975	0.9982	0.9979
0.04	2.0	3918	0.0050	0.9975	0.9982	0.9979
0.0253	3.0	5877	0.0015	1.0	1.0	1.0
0.0175	4.0	7836	0.0003	1.0	1.0	1.0
0.0134	5.0	9795	0.0001	1.0	1.0	1.0
0.0107	6.0	11754	0.0001	1.0	1.0	1.0
0.0081	7.0	13713	0.0012	1.0	1.0	1.0
0.0062	8.0	15672	0.0000	1.0	1.0	1.0
0.0061	9.0	17631	0.0001	1.0	1.0	1.0
0.0044	10.0	19590	0.0002	1.0	1.0	1.0
0.0041	11.0	21549	0.0000	1.0	1.0	1.0
0.0034	12.0	23508	0.0000	1.0	1.0	1.0
0.0029	13.0	25467	0.0000	1.0	1.0	1.0
0.0016	14.0	27426	0.0000	1.0	1.0	1.0
0.0019	15.0	29385	0.0140	0.9975	0.9982	0.9979
0.0018	16.0	31344	0.0001	1.0	1.0	1.0
0.0012	17.0	33303	0.0000	1.0	1.0	1.0
0.0013	18.0	35262	0.0000	1.0	1.0	1.0
0.0008	19.0	37221	0.0000	1.0	1.0	1.0
0.0011	20.0	39180	0.0000	1.0	1.0	1.0
0.0005	21.0	41139	0.0007	1.0	1.0	1.0
0.0009	22.0	43098	0.0000	1.0	1.0	1.0
0.0004	23.0	45057	0.0000	1.0	1.0	1.0
0.0004	24.0	47016	0.0000	1.0	1.0	1.0

Framework versions

• Transformers 4.26.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.9.0
• Tokenizers 0.13.2