results

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: 2.9905
• Accuracy: 0.5067

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	132	0.6630	0.6267
No log	2.0	264	0.6697	0.6267
No log	3.0	396	0.6605	0.6267
0.6686	4.0	528	0.6797	0.6267
0.6686	5.0	660	0.6599	0.5733
0.6686	6.0	792	0.6702	0.58
0.6686	7.0	924	0.7593	0.5267
0.6278	8.0	1056	0.7622	0.6
0.6278	9.0	1188	0.8147	0.6067
0.6278	10.0	1320	1.2285	0.5733
0.6278	11.0	1452	1.2681	0.58
0.5453	12.0	1584	1.4571	0.5667
0.5453	13.0	1716	1.5210	0.5467
0.5453	14.0	1848	1.6548	0.5733
0.5453	15.0	1980	1.6931	0.5667
0.4703	16.0	2112	1.8606	0.5867
0.4703	17.0	2244	1.9779	0.56
0.4703	18.0	2376	2.3998	0.4933
0.3567	19.0	2508	2.2930	0.5
0.3567	20.0	2640	2.6606	0.4933
0.3567	21.0	2772	2.4945	0.4933
0.3567	22.0	2904	2.6740	0.5133
0.2371	23.0	3036	2.7472	0.5
0.2371	24.0	3168	2.7916	0.5
0.2371	25.0	3300	2.8399	0.5
0.2371	26.0	3432	2.8665	0.52
0.1688	27.0	3564	2.9246	0.5133
0.1688	28.0	3696	2.9675	0.5
0.1688	29.0	3828	2.9967	0.5067
0.1688	30.0	3960	2.9905	0.5067

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3