distilbert_sa_GLUE_Experiment_data_aug_mrpc_192

This model is a fine-tuned version of distilbert-base-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: 256
• eval_batch_size: 256
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
0.2446	1.0	980	0.0556	0.9877	0.9911	0.9894
0.0516	2.0	1960	0.0106	0.9951	0.9964	0.9958
0.0236	3.0	2940	0.0011	1.0	1.0	1.0
0.0149	4.0	3920	0.0010	1.0	1.0	1.0
0.0102	5.0	4900	0.0003	1.0	1.0	1.0
0.0067	6.0	5880	0.0002	1.0	1.0	1.0
0.005	7.0	6860	0.0001	1.0	1.0	1.0
0.0042	8.0	7840	0.0000	1.0	1.0	1.0
0.0034	9.0	8820	0.0001	1.0	1.0	1.0
0.0025	10.0	9800	0.0000	1.0	1.0	1.0
0.0024	11.0	10780	0.0001	1.0	1.0	1.0
0.0026	12.0	11760	0.0000	1.0	1.0	1.0
0.0019	13.0	12740	0.0000	1.0	1.0	1.0
0.0014	14.0	13720	0.0000	1.0	1.0	1.0
0.0013	15.0	14700	0.0000	1.0	1.0	1.0
0.0014	16.0	15680	0.0000	1.0	1.0	1.0
0.0012	17.0	16660	0.0000	1.0	1.0	1.0
0.0009	18.0	17640	0.0000	1.0	1.0	1.0
0.0007	19.0	18620	0.0000	1.0	1.0	1.0
0.0008	20.0	19600	0.0000	1.0	1.0	1.0
0.0008	21.0	20580	0.0000	1.0	1.0	1.0
0.0006	22.0	21560	0.0000	1.0	1.0	1.0
0.0007	23.0	22540	0.0000	1.0	1.0	1.0
0.0003	24.0	23520	0.0000	1.0	1.0	1.0
0.0005	25.0	24500	0.0000	1.0	1.0	1.0
0.0005	26.0	25480	0.0000	1.0	1.0	1.0
0.0003	27.0	26460	0.0001	1.0	1.0	1.0
0.0002	28.0	27440	0.0000	1.0	1.0	1.0
0.0003	29.0	28420	0.0000	1.0	1.0	1.0
0.0003	30.0	29400	0.0000	1.0	1.0	1.0
0.0001	31.0	30380	0.0000	1.0	1.0	1.0
0.0004	32.0	31360	0.0000	1.0	1.0	1.0
0.0003	33.0	32340	0.0000	1.0	1.0	1.0
0.0001	34.0	33320	0.0000	1.0	1.0	1.0
0.0001	35.0	34300	0.0000	1.0	1.0	1.0
0.0001	36.0	35280	0.0000	1.0	1.0	1.0
0.0002	37.0	36260	0.0000	1.0	1.0	1.0
0.0001	38.0	37240	0.0000	1.0	1.0	1.0
0.0002	39.0	38220	0.0000	1.0	1.0	1.0
0.0001	40.0	39200	0.0000	1.0	1.0	1.0
0.0	41.0	40180	0.0000	1.0	1.0	1.0
0.0	42.0	41160	0.0000	1.0	1.0	1.0
0.0001	43.0	42140	0.0000	1.0	1.0	1.0
0.0	44.0	43120	0.0000	1.0	1.0	1.0
0.0	45.0	44100	0.0000	1.0	1.0	1.0
0.0	46.0	45080	0.0000	1.0	1.0	1.0
0.0	47.0	46060	0.0000	1.0	1.0	1.0
0.0	48.0	47040	0.0000	1.0	1.0	1.0
0.0	49.0	48020	0.0000	1.0	1.0	1.0
0.0	50.0	49000	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