N_distilbert_sst5_padding20model

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: 4.1658
• Accuracy: 0.4986

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3013	1.0	534	1.2755	0.4186
1.0414	2.0	1068	1.1110	0.5163
0.8427	3.0	1602	1.1757	0.5213
0.6773	4.0	2136	1.2838	0.5186
0.5227	5.0	2670	1.5249	0.5036
0.3869	6.0	3204	1.7458	0.5023
0.291	7.0	3738	2.0381	0.5036
0.21	8.0	4272	2.2499	0.5077
0.1691	9.0	4806	2.4262	0.5068
0.1443	10.0	5340	2.8024	0.5
0.1228	11.0	5874	3.1036	0.5
0.1009	12.0	6408	3.3389	0.4977
0.0853	13.0	6942	3.4864	0.4977
0.0595	14.0	7476	3.6371	0.5041
0.0402	15.0	8010	3.8422	0.5005
0.0316	16.0	8544	3.9363	0.5054
0.0242	17.0	9078	4.0754	0.4946
0.0179	18.0	9612	4.0945	0.5009
0.0197	19.0	10146	4.1188	0.5005
0.0142	20.0	10680	4.1658	0.4986

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3