spellcorrector_1209_v5

This model is a fine-tuned version of google/canine-s on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0129
• Precision: 0.9884
• Recall: 0.9845
• F1: 0.9865
• Accuracy: 0.9958

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	Precision	Recall	F1	Accuracy
0.2592	1.0	1951	0.1973	0.7990	0.7403	0.7686	0.9462
0.2036	2.0	3902	0.1430	0.8304	0.7969	0.8133	0.9591
0.1643	3.0	5853	0.1090	0.8775	0.8292	0.8527	0.9688
0.1339	4.0	7804	0.0898	0.8971	0.8539	0.8750	0.9743
0.1143	5.0	9755	0.0788	0.9104	0.8768	0.8933	0.9773
0.0996	6.0	11706	0.0648	0.9240	0.8929	0.9082	0.9810
0.0874	7.0	13657	0.0568	0.9349	0.9035	0.9189	0.9829
0.0797	8.0	15608	0.0496	0.9439	0.9215	0.9326	0.9851
0.0696	9.0	17559	0.0426	0.9538	0.9289	0.9412	0.9868
0.0647	10.0	19510	0.0385	0.9596	0.9372	0.9482	0.9880
0.0532	11.0	21461	0.0335	0.9636	0.9465	0.9550	0.9895
0.0481	12.0	23412	0.0298	0.9704	0.9570	0.9636	0.9907
0.0443	13.0	25363	0.0240	0.9745	0.9654	0.9699	0.9923
0.0414	14.0	27314	0.0229	0.9795	0.9671	0.9732	0.9926
0.0369	15.0	29265	0.0195	0.9809	0.9737	0.9773	0.9938
0.0339	16.0	31216	0.0171	0.9831	0.9778	0.9805	0.9944
0.0312	17.0	33167	0.0156	0.9859	0.9797	0.9828	0.9949
0.0276	18.0	35118	0.0140	0.9874	0.9821	0.9847	0.9954
0.0277	19.0	37069	0.0133	0.9880	0.9840	0.9860	0.9957
0.0253	20.0	39020	0.0129	0.9884	0.9845	0.9865	0.9958

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3