distilbert_sa_GLUE_Experiment_data_aug_mrpc_96

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
0.3242	1.0	980	0.0830	0.9804	0.9857	0.9830
0.0843	2.0	1960	0.0355	0.9828	0.9875	0.9852
0.0431	3.0	2940	0.0105	1.0	1.0	1.0
0.0268	4.0	3920	0.0046	1.0	1.0	1.0
0.019	5.0	4900	0.0015	1.0	1.0	1.0
0.0141	6.0	5880	0.0011	1.0	1.0	1.0
0.0115	7.0	6860	0.0007	1.0	1.0	1.0
0.0094	8.0	7840	0.0004	1.0	1.0	1.0
0.0078	9.0	8820	0.0004	1.0	1.0	1.0
0.0056	10.0	9800	0.0006	1.0	1.0	1.0
0.0056	11.0	10780	0.0001	1.0	1.0	1.0
0.0039	12.0	11760	0.0001	1.0	1.0	1.0
0.0038	13.0	12740	0.0001	1.0	1.0	1.0
0.0029	14.0	13720	0.0000	1.0	1.0	1.0
0.0026	15.0	14700	0.0000	1.0	1.0	1.0
0.0025	16.0	15680	0.0000	1.0	1.0	1.0
0.0019	17.0	16660	0.0000	1.0	1.0	1.0
0.0017	18.0	17640	0.0000	1.0	1.0	1.0
0.0015	19.0	18620	0.0000	1.0	1.0	1.0
0.0013	20.0	19600	0.0000	1.0	1.0	1.0
0.0013	21.0	20580	0.0000	1.0	1.0	1.0
0.0013	22.0	21560	0.0000	1.0	1.0	1.0
0.0012	23.0	22540	0.0000	1.0	1.0	1.0
0.001	24.0	23520	0.0000	1.0	1.0	1.0
0.0008	25.0	24500	0.0000	1.0	1.0	1.0
0.0007	26.0	25480	0.0000	1.0	1.0	1.0
0.0006	27.0	26460	0.0000	1.0	1.0	1.0
0.0007	28.0	27440	0.0000	1.0	1.0	1.0
0.0007	29.0	28420	0.0000	1.0	1.0	1.0
0.0005	30.0	29400	0.0000	1.0	1.0	1.0
0.0004	31.0	30380	0.0000	1.0	1.0	1.0
0.0005	32.0	31360	0.0000	1.0	1.0	1.0
0.0004	33.0	32340	0.0000	1.0	1.0	1.0
0.0003	34.0	33320	0.0000	1.0	1.0	1.0
0.0004	35.0	34300	0.0000	1.0	1.0	1.0
0.0002	36.0	35280	0.0000	1.0	1.0	1.0
0.0003	37.0	36260	0.0000	1.0	1.0	1.0
0.0003	38.0	37240	0.0000	1.0	1.0	1.0
0.0003	39.0	38220	0.0000	1.0	1.0	1.0
0.0002	40.0	39200	0.0000	1.0	1.0	1.0
0.0002	41.0	40180	0.0000	1.0	1.0	1.0
0.0	42.0	41160	0.0000	1.0	1.0	1.0
0.0002	43.0	42140	0.0000	1.0	1.0	1.0
0.0002	44.0	43120	0.0000	1.0	1.0	1.0
0.0001	45.0	44100	0.0000	1.0	1.0	1.0
0.0001	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
0.0001	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