plbart-finetuned-unitTest-v1

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

• Loss: 1.4949
• Bleu: 0.0000

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: 1
• eval_batch_size: 1
• seed: 42
• 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	Bleu
1.2819	1.0	918	0.8663	0.0000
0.7575	2.0	1836	0.8740	0.0000
0.6118	3.0	2754	0.8570	0.0000
0.506	4.0	3672	0.9254	0.0000
0.4114	5.0	4590	0.9183	0.0000
0.3554	6.0	5508	0.9901	0.0000
0.274	7.0	6426	1.0385	0.0000
0.248	8.0	7344	1.0427	0.0000
0.2008	9.0	8262	1.0427	0.0000
0.1883	10.0	9180	1.1100	0.0000
0.1572	11.0	10098	1.1253	0.0000
0.1349	12.0	11016	1.1110	0.0000
0.1139	13.0	11934	1.1399	0.0000
0.1012	14.0	12852	1.1812	0.0000
0.0924	15.0	13770	1.2108	0.0000
0.078	16.0	14688	1.2008	0.0000
0.0738	17.0	15606	1.2454	0.0000
0.0627	18.0	16524	1.2557	0.0000
0.0559	19.0	17442	1.2442	0.0000
0.0502	20.0	18360	1.2724	0.0000
0.0478	21.0	19278	1.2731	0.0000
0.044	22.0	20196	1.2850	0.0000
0.038	23.0	21114	1.2929	0.0000
0.0357	24.0	22032	1.3371	0.0000
0.0316	25.0	22950	1.3470	0.0000
0.0285	26.0	23868	1.3976	0.0000
0.0269	27.0	24786	1.3808	0.0000
0.0258	28.0	25704	1.4028	0.0000
0.0228	29.0	26622	1.4032	0.0000
0.0219	30.0	27540	1.4082	0.0000
0.0207	31.0	28458	1.4250	0.0000
0.0186	32.0	29376	1.4383	0.0000
0.0162	33.0	30294	1.4060	0.0000
0.0151	34.0	31212	1.4416	0.0000
0.015	35.0	32130	1.4397	0.0000
0.0146	36.0	33048	1.4644	0.0000
0.0107	37.0	33966	1.4560	0.0000
0.0116	38.0	34884	1.4565	0.0000
0.0116	39.0	35802	1.4707	0.0000
0.0105	40.0	36720	1.4684	0.0000
0.0084	41.0	37638	1.4776	0.0000
0.0098	42.0	38556	1.4885	0.0000
0.0078	43.0	39474	1.4916	0.0000
0.0071	44.0	40392	1.4891	0.0000
0.0071	45.0	41310	1.4883	0.0000
0.0071	46.0	42228	1.4880	0.0000
0.0069	47.0	43146	1.4867	0.0000
0.0068	48.0	44064	1.4936	0.0000
0.0061	49.0	44982	1.4943	0.0000
0.0062	50.0	45900	1.4949	0.0000

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3