distilbert-base-uncased-textclassification_adalora

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

• Loss: 0.6697
• Precision: 0.6503
• Recall: 0.5072
• F1: 0.5699
• Accuracy: 0.9524

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: 16
• eval_batch_size: 16
• 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	Precision	Recall	F1	Accuracy
No log	1.0	213	1.9179	0.4803	0.2620	0.3390	0.9371
No log	2.0	426	1.6876	0.5057	0.3194	0.3915	0.9404
1.7592	3.0	639	1.4144	0.5161	0.3445	0.4132	0.9420
1.7592	4.0	852	1.1653	0.5455	0.3517	0.4276	0.9428
1.1731	5.0	1065	1.0656	0.575	0.3852	0.4613	0.9443
1.1731	6.0	1278	0.9946	0.5878	0.4163	0.4874	0.9461
1.1731	7.0	1491	0.9620	0.6467	0.4139	0.5047	0.9464
0.8895	8.0	1704	0.9450	0.6587	0.4294	0.5199	0.9473
0.8895	9.0	1917	0.9187	0.6382	0.4557	0.5318	0.9488
0.8124	10.0	2130	0.9042	0.6528	0.4522	0.5343	0.9493
0.8124	11.0	2343	0.8847	0.6443	0.4701	0.5436	0.9500
0.7741	12.0	2556	0.8773	0.6594	0.4677	0.5472	0.9502
0.7741	13.0	2769	0.8642	0.6672	0.4653	0.5483	0.9502
0.7741	14.0	2982	0.8439	0.6694	0.4821	0.5605	0.9514
0.7346	15.0	3195	0.8381	0.6735	0.4737	0.5562	0.9512
0.7346	16.0	3408	0.8199	0.6773	0.4844	0.5649	0.9517
0.6966	17.0	3621	0.8007	0.6744	0.4856	0.5647	0.9521
0.6966	18.0	3834	0.7845	0.6618	0.4916	0.5642	0.9520
0.6575	19.0	4047	0.7677	0.6491	0.5	0.5649	0.9522
0.6575	20.0	4260	0.7573	0.6624	0.4904	0.5636	0.9524
0.6575	21.0	4473	0.7419	0.6561	0.4928	0.5628	0.9522
0.6218	22.0	4686	0.7282	0.6435	0.4988	0.5620	0.9522
0.6218	23.0	4899	0.7142	0.6346	0.5048	0.5623	0.9520
0.5894	24.0	5112	0.7173	0.6474	0.4964	0.5619	0.9521
0.5894	25.0	5325	0.7132	0.6562	0.4976	0.5660	0.9526
0.5728	26.0	5538	0.7051	0.6453	0.5048	0.5664	0.9523
0.5728	27.0	5751	0.7032	0.6462	0.5024	0.5653	0.9524
0.5728	28.0	5964	0.6984	0.6405	0.5072	0.5661	0.9524
0.5629	29.0	6177	0.6973	0.6502	0.5024	0.5668	0.9523
0.5629	30.0	6390	0.6928	0.6459	0.5084	0.5689	0.9527
0.5543	31.0	6603	0.6935	0.6483	0.5072	0.5691	0.9528
0.5543	32.0	6816	0.6893	0.6448	0.5060	0.5670	0.9526
0.5465	33.0	7029	0.6893	0.6593	0.5024	0.5703	0.9524
0.5465	34.0	7242	0.6863	0.6594	0.5048	0.5718	0.9526
0.5465	35.0	7455	0.6829	0.6543	0.5072	0.5714	0.9526
0.5414	36.0	7668	0.6780	0.6464	0.5096	0.5699	0.9528
0.5414	37.0	7881	0.6776	0.6508	0.5084	0.5709	0.9526
0.5341	38.0	8094	0.6764	0.6549	0.5084	0.5724	0.9525
0.5341	39.0	8307	0.6749	0.6549	0.5084	0.5724	0.9526
0.5301	40.0	8520	0.6773	0.6640	0.5012	0.5712	0.9525
0.5301	41.0	8733	0.6730	0.6518	0.5084	0.5712	0.9525
0.5301	42.0	8946	0.6717	0.6509	0.5108	0.5724	0.9526
0.5268	43.0	9159	0.6721	0.6544	0.5096	0.5730	0.9525
0.5268	44.0	9372	0.6694	0.6480	0.5108	0.5712	0.9526
0.5236	45.0	9585	0.6709	0.6528	0.5084	0.5716	0.9525
0.5236	46.0	9798	0.6694	0.6494	0.5096	0.5710	0.9525
0.5231	47.0	10011	0.6693	0.6514	0.5096	0.5718	0.9525
0.5231	48.0	10224	0.6696	0.6503	0.5072	0.5699	0.9524
0.5231	49.0	10437	0.6699	0.6513	0.5072	0.5703	0.9524
0.5224	50.0	10650	0.6697	0.6503	0.5072	0.5699	0.9524

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.0.0+cu117
• Datasets 2.16.1
• Tokenizers 0.15.0