N_distilbert_sst5_padding10model

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: 4.1236
• Accuracy: 0.5023

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
1.2881	1.0	534	1.2448	0.4348
1.0196	2.0	1068	1.1144	0.5208
0.8169	3.0	1602	1.1867	0.5249
0.6703	4.0	2136	1.3514	0.5195
0.5051	5.0	2670	1.6276	0.4946
0.3893	6.0	3204	1.8058	0.4910
0.2916	7.0	3738	1.9627	0.5009
0.219	8.0	4272	2.1724	0.5036
0.1789	9.0	4806	2.4518	0.5027
0.1443	10.0	5340	2.7508	0.4986
0.1206	11.0	5874	3.0702	0.4964
0.0969	12.0	6408	3.2655	0.4928
0.0755	13.0	6942	3.3892	0.5063
0.0643	14.0	7476	3.7077	0.4986
0.042	15.0	8010	3.7313	0.4977
0.0386	16.0	8544	3.9008	0.4977
0.0275	17.0	9078	4.0575	0.4991
0.0227	18.0	9612	4.0796	0.5072
0.0203	19.0	10146	4.1166	0.5018
0.0161	20.0	10680	4.1236	0.5023

Framework versions

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