Misinformation-Covid-LowLearningRatebert-base-multilingual-cased

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

• Loss: 0.5774
• F1: 0.0488

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-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.6829	1.0	189	0.6704	0.1463
0.673	2.0	378	0.6340	0.0784
0.6543	3.0	567	0.6453	0.0
0.6519	4.0	756	0.6439	0.0
0.6598	5.0	945	0.6427	0.0
0.65	6.0	1134	0.6416	0.0
0.673	7.0	1323	0.6415	0.0
0.6573	8.0	1512	0.6411	0.0
0.6641	9.0	1701	0.6404	0.0
0.667	10.0	1890	0.6398	0.0
0.6646	11.0	2079	0.6387	0.0
0.6552	12.0	2268	0.6377	0.0
0.6617	13.0	2457	0.6368	0.0
0.649	14.0	2646	0.6352	0.0
0.663	15.0	2835	0.6338	0.0
0.6506	16.0	3024	0.6322	0.0
0.6627	17.0	3213	0.6306	0.0
0.6492	18.0	3402	0.6288	0.0
0.6457	19.0	3591	0.6262	0.0
0.6448	20.0	3780	0.6238	0.0
0.6431	21.0	3969	0.6211	0.0
0.6412	22.0	4158	0.6189	0.0
0.6333	23.0	4347	0.6151	0.0
0.6435	24.0	4536	0.6121	0.0
0.6325	25.0	4725	0.6092	0.0
0.6271	26.0	4914	0.6047	0.0
0.6234	27.0	5103	0.6018	0.0
0.6185	28.0	5292	0.5993	0.0
0.6274	29.0	5481	0.5964	0.0
0.6129	30.0	5670	0.5942	0.0
0.6204	31.0	5859	0.5921	0.0
0.6044	32.0	6048	0.5913	0.0
0.6103	33.0	6237	0.5891	0.0
0.6005	34.0	6426	0.5868	0.0
0.6058	35.0	6615	0.5865	0.0
0.6179	36.0	6804	0.5846	0.0
0.6077	37.0	6993	0.5835	0.0
0.5964	38.0	7182	0.5832	0.0
0.6106	39.0	7371	0.5813	0.0
0.5865	40.0	7560	0.5816	0.0
0.6142	41.0	7749	0.5795	0.0
0.5903	42.0	7938	0.5790	0.0
0.5926	43.0	8127	0.5790	0.0
0.6077	44.0	8316	0.5786	0.0
0.6025	45.0	8505	0.5780	0.0
0.604	46.0	8694	0.5771	0.0488
0.5875	47.0	8883	0.5774	0.0488
0.5797	48.0	9072	0.5775	0.0488
0.6054	49.0	9261	0.5775	0.0488
0.5974	50.0	9450	0.5774	0.0488

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.2
• Datasets 2.12.0
• Tokenizers 0.13.3