comic-name-classification

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: 0.0448
• Accuracy: 0.9937

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: 0.000125
• train_batch_size: 32
• eval_batch_size: 32
• 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	Accuracy
No log	1.0	25	0.0317	0.9933
No log	2.0	50	0.0342	0.9933
No log	3.0	75	0.0339	0.9933
No log	4.0	100	0.0361	0.9941
No log	5.0	125	0.0367	0.9945
No log	6.0	150	0.0372	0.9941
No log	7.0	175	0.0388	0.9945
No log	8.0	200	0.0365	0.9941
No log	9.0	225	0.0359	0.9941
No log	10.0	250	0.0385	0.9941
No log	11.0	275	0.0380	0.9941
No log	12.0	300	0.0394	0.9937
No log	13.0	325	0.0389	0.9941
No log	14.0	350	0.0398	0.9941
No log	15.0	375	0.0398	0.9937
No log	16.0	400	0.0399	0.9941
No log	17.0	425	0.0419	0.9941
No log	18.0	450	0.0409	0.9941
No log	19.0	475	0.0415	0.9937
0.0037	20.0	500	0.0418	0.9941
0.0037	21.0	525	0.0430	0.9941
0.0037	22.0	550	0.0419	0.9941
0.0037	23.0	575	0.0434	0.9941
0.0037	24.0	600	0.0443	0.9941
0.0037	25.0	625	0.0447	0.9941
0.0037	26.0	650	0.0444	0.9937
0.0037	27.0	675	0.0438	0.9937
0.0037	28.0	700	0.0431	0.9941
0.0037	29.0	725	0.0426	0.9941
0.0037	30.0	750	0.0434	0.9941
0.0037	31.0	775	0.0442	0.9941
0.0037	32.0	800	0.0423	0.9941
0.0037	33.0	825	0.0423	0.9941
0.0037	34.0	850	0.0419	0.9941
0.0037	35.0	875	0.0422	0.9941
0.0037	36.0	900	0.0433	0.9941
0.0037	37.0	925	0.0434	0.9941
0.0037	38.0	950	0.0443	0.9941
0.0037	39.0	975	0.0449	0.9937
0.002	40.0	1000	0.0452	0.9937
0.002	41.0	1025	0.0459	0.9941
0.002	42.0	1050	0.0463	0.9941
0.002	43.0	1075	0.0449	0.9937
0.002	44.0	1100	0.0443	0.9941
0.002	45.0	1125	0.0442	0.9941
0.002	46.0	1150	0.0445	0.9941
0.002	47.0	1175	0.0446	0.9941
0.002	48.0	1200	0.0447	0.9937
0.002	49.0	1225	0.0448	0.9937
0.002	50.0	1250	0.0448	0.9937

Framework versions

• PEFT 0.7.1
• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0