N_distilbert_sst5_padding80model

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: 3.8771
• Accuracy: 0.5041

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
1.3362	1.0	534	1.2555	0.4326
1.0552	2.0	1068	1.1173	0.5045
0.8719	3.0	1602	1.1703	0.5154
0.7096	4.0	2136	1.2926	0.5104
0.5637	5.0	2670	1.5040	0.5036
0.425	6.0	3204	1.6993	0.4932
0.3294	7.0	3738	1.9342	0.5109
0.2374	8.0	4272	2.0846	0.5050
0.2032	9.0	4806	2.3320	0.4964
0.1772	10.0	5340	2.6345	0.4900
0.1419	11.0	5874	2.8924	0.4914
0.1251	12.0	6408	3.1132	0.4950
0.098	13.0	6942	3.2396	0.5050
0.0869	14.0	7476	3.3763	0.5023
0.0613	15.0	8010	3.5375	0.4977
0.0477	16.0	8544	3.6446	0.5014
0.0347	17.0	9078	3.7261	0.4959
0.0361	18.0	9612	3.7923	0.4982
0.0258	19.0	10146	3.8617	0.5027
0.0212	20.0	10680	3.8771	0.5041

Framework versions

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