distilbert_sa_GLUE_Experiment_data_aug_mrpc_384

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
0.1771	1.0	980	0.0049	1.0	1.0	1.0
0.0321	2.0	1960	0.0009	1.0	1.0	1.0
0.0154	3.0	2940	0.0001	1.0	1.0	1.0
0.0086	4.0	3920	0.0009	1.0	1.0	1.0
0.0062	5.0	4900	0.0000	1.0	1.0	1.0
0.0039	6.0	5880	0.0000	1.0	1.0	1.0
0.0039	7.0	6860	0.0000	1.0	1.0	1.0
0.0028	8.0	7840	0.0000	1.0	1.0	1.0
0.0022	9.0	8820	0.0000	1.0	1.0	1.0
0.0018	10.0	9800	0.0000	1.0	1.0	1.0
0.002	11.0	10780	0.0000	1.0	1.0	1.0
0.0011	12.0	11760	0.0000	1.0	1.0	1.0
0.0015	13.0	12740	0.0000	1.0	1.0	1.0
0.0011	14.0	13720	0.0000	1.0	1.0	1.0
0.0011	15.0	14700	0.0000	1.0	1.0	1.0
0.0008	16.0	15680	0.0000	1.0	1.0	1.0
0.0009	17.0	16660	0.0000	1.0	1.0	1.0
0.0007	18.0	17640	0.0001	1.0	1.0	1.0
0.0006	19.0	18620	0.0000	1.0	1.0	1.0
0.0006	20.0	19600	0.0000	1.0	1.0	1.0
0.0004	21.0	20580	0.0000	1.0	1.0	1.0
0.0004	22.0	21560	0.0000	1.0	1.0	1.0
0.0002	23.0	22540	0.0000	1.0	1.0	1.0
0.0004	24.0	23520	0.0000	1.0	1.0	1.0
0.0003	25.0	24500	0.0000	1.0	1.0	1.0
0.0004	26.0	25480	0.0000	1.0	1.0	1.0
0.0003	27.0	26460	0.0000	1.0	1.0	1.0
0.0002	28.0	27440	0.0000	1.0	1.0	1.0
0.0002	29.0	28420	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