nerel-bio-RuBioRoBERTa-base

This model is a fine-tuned version of alexyalunin/RuBioRoBERTa on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5262
• Precision: 0.8251
• Recall: 0.8335
• F1: 0.8293
• Accuracy: 0.8827

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: 5e-05
• train_batch_size: 6
• eval_batch_size: 6
• seed: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	102	1.7932	0.4125	0.4094	0.4110	0.5484
No log	2.0	204	0.5751	0.7711	0.7635	0.7673	0.8392
No log	3.0	306	0.4426	0.8053	0.8163	0.8107	0.8727
No log	4.0	408	0.4545	0.8070	0.8049	0.8060	0.8707
0.8666	5.0	510	0.4854	0.8100	0.8024	0.8062	0.8693
0.8666	6.0	612	0.4791	0.8194	0.8210	0.8202	0.8805
0.8666	7.0	714	0.4975	0.8202	0.8306	0.8254	0.8816
0.8666	8.0	816	0.4997	0.8217	0.8304	0.8260	0.8817
0.8666	9.0	918	0.5237	0.8237	0.8318	0.8277	0.8821
0.0548	10.0	1020	0.5262	0.8251	0.8335	0.8293	0.8827

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2