Misinformation-Covid-LowLearningRatebert-base-chinese

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

• Loss: 0.5999
• F1: 0.2128

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
0.6765	1.0	189	0.6464	0.0
0.6809	2.0	378	0.6449	0.0
0.6734	3.0	567	0.6651	0.0
0.6827	4.0	756	0.6684	0.0
0.7095	5.0	945	0.6532	0.0
0.7	6.0	1134	0.6646	0.0
0.7192	7.0	1323	0.6497	0.0
0.6877	8.0	1512	0.6446	0.0
0.6831	9.0	1701	0.6305	0.0571
0.6633	10.0	1890	0.6203	0.1622
0.6668	11.0	2079	0.6219	0.1622
0.6482	12.0	2268	0.6242	0.1111
0.6543	13.0	2457	0.6117	0.15
0.6492	14.0	2646	0.6236	0.1622
0.6624	15.0	2835	0.6233	0.1622
0.6525	16.0	3024	0.6134	0.15
0.6466	17.0	3213	0.6118	0.1905
0.6406	18.0	3402	0.6191	0.15
0.6479	19.0	3591	0.6216	0.1538
0.6488	20.0	3780	0.6076	0.2128
0.6352	21.0	3969	0.6062	0.2174
0.6213	22.0	4158	0.6042	0.2174
0.6285	23.0	4347	0.6100	0.2326
0.6298	24.0	4536	0.6076	0.2128
0.6473	25.0	4725	0.6058	0.2128
0.5972	26.0	4914	0.6065	0.2222
0.6118	27.0	5103	0.6001	0.25
0.6116	28.0	5292	0.6059	0.2128
0.6289	29.0	5481	0.5992	0.25
0.5932	30.0	5670	0.6006	0.25
0.6076	31.0	5859	0.6009	0.2128
0.6033	32.0	6048	0.6082	0.2128
0.6235	33.0	6237	0.6023	0.2128
0.6237	34.0	6426	0.6079	0.2222
0.6176	35.0	6615	0.6081	0.2222
0.646	36.0	6804	0.6019	0.2128
0.6233	37.0	6993	0.6020	0.2128
0.6004	38.0	7182	0.6040	0.2174
0.6159	39.0	7371	0.5963	0.2449
0.5747	40.0	7560	0.6011	0.2174
0.6216	41.0	7749	0.5954	0.2449
0.5893	42.0	7938	0.5974	0.2083
0.5887	43.0	8127	0.5993	0.2128
0.5756	44.0	8316	0.5993	0.2128
0.6204	45.0	8505	0.5982	0.2083
0.584	46.0	8694	0.5966	0.2449
0.5809	47.0	8883	0.5989	0.2083
0.5873	48.0	9072	0.6002	0.2128
0.5999	49.0	9261	0.6001	0.2128
0.5888	50.0	9450	0.5999	0.2128

Framework versions

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