rubert-tiny2-odonata-extended-ner

This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0063
• Precision: 0.7067
• Recall: 0.7681
• F1: 0.7361
• Accuracy: 0.9981

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	32	0.1795	0.0	0.0	0.0	0.9961
No log	2.0	64	0.0386	0.0	0.0	0.0	0.9961
No log	3.0	96	0.0316	0.0	0.0	0.0	0.9961
No log	4.0	128	0.0292	0.0	0.0	0.0	0.9961
No log	5.0	160	0.0231	0.0	0.0	0.0	0.9961
No log	6.0	192	0.0152	0.6923	0.1304	0.2195	0.9964
No log	7.0	224	0.0123	0.6212	0.5942	0.6074	0.9971
No log	8.0	256	0.0108	0.5946	0.6377	0.6154	0.9970
No log	9.0	288	0.0099	0.6269	0.6087	0.6176	0.9972
No log	10.0	320	0.0092	0.5921	0.6522	0.6207	0.9971
No log	11.0	352	0.0087	0.6267	0.6812	0.6528	0.9974
No log	12.0	384	0.0083	0.65	0.7536	0.6980	0.9977
No log	13.0	416	0.0079	0.6456	0.7391	0.6892	0.9976
No log	14.0	448	0.0076	0.6375	0.7391	0.6846	0.9977
No log	15.0	480	0.0074	0.6667	0.7826	0.72	0.9979
0.0795	16.0	512	0.0072	0.6933	0.7536	0.7222	0.9980
0.0795	17.0	544	0.0071	0.6420	0.7536	0.6933	0.9978
0.0795	18.0	576	0.0069	0.6806	0.7101	0.6950	0.9979
0.0795	19.0	608	0.0068	0.68	0.7391	0.7083	0.9980
0.0795	20.0	640	0.0067	0.68	0.7391	0.7083	0.9980
0.0795	21.0	672	0.0066	0.6842	0.7536	0.7172	0.9980
0.0795	22.0	704	0.0065	0.6933	0.7536	0.7222	0.9980
0.0795	23.0	736	0.0065	0.6849	0.7246	0.7042	0.9980
0.0795	24.0	768	0.0064	0.7027	0.7536	0.7273	0.9981
0.0795	25.0	800	0.0063	0.7027	0.7536	0.7273	0.9981
0.0795	26.0	832	0.0063	0.7162	0.7681	0.7413	0.9981
0.0795	27.0	864	0.0063	0.7162	0.7681	0.7413	0.9981
0.0795	28.0	896	0.0063	0.7027	0.7536	0.7273	0.9981
0.0795	29.0	928	0.0063	0.7067	0.7681	0.7361	0.9981
0.0795	30.0	960	0.0063	0.7067	0.7681	0.7361	0.9981

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1+cpu
• Datasets 2.19.2
• Tokenizers 0.19.1