roberta-finetuned-WebClassification-v2-smalllinguaMultiv2

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8644
• Accuracy: 0.8387
• F1: 0.8387
• Precision: 0.8387
• Recall: 0.8387

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	95	2.3654	0.4409	0.4409	0.4409	0.4409
No log	2.0	190	1.8455	0.5269	0.5269	0.5269	0.5269
No log	3.0	285	1.4468	0.6344	0.6344	0.6344	0.6344
No log	4.0	380	1.1099	0.7419	0.7419	0.7419	0.7419
No log	5.0	475	1.0515	0.7634	0.7634	0.7634	0.7634
1.6355	6.0	570	0.9938	0.7312	0.7312	0.7312	0.7312
1.6355	7.0	665	0.8275	0.7957	0.7957	0.7957	0.7957
1.6355	8.0	760	0.8344	0.7957	0.7957	0.7957	0.7957
1.6355	9.0	855	0.8516	0.8065	0.8065	0.8065	0.8065
1.6355	10.0	950	0.8723	0.7957	0.7957	0.7957	0.7957
0.2827	11.0	1045	0.8644	0.8387	0.8387	0.8387	0.8387
0.2827	12.0	1140	0.9343	0.8065	0.8065	0.8065	0.8065
0.2827	13.0	1235	1.0181	0.7957	0.7957	0.7957	0.7957
0.2827	14.0	1330	1.0068	0.7957	0.7957	0.7957	0.7957
0.2827	15.0	1425	1.0085	0.8065	0.8065	0.8065	0.8065
0.0485	16.0	1520	1.0257	0.8280	0.8280	0.8280	0.8280
0.0485	17.0	1615	1.0305	0.8172	0.8172	0.8172	0.8172
0.0485	18.0	1710	1.0648	0.7957	0.7957	0.7957	0.7957
0.0485	19.0	1805	1.0677	0.7957	0.7957	0.7957	0.7957
0.0485	20.0	1900	1.0687	0.7957	0.7957	0.7957	0.7957

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3