text_to_subfunction_v7

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: 2.9393
• F1: 0.4657

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: 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
3.0953	1.0	4995	2.9647	0.1986
2.2212	2.0	9990	2.3916	0.3411
1.7716	3.0	14985	2.1448	0.3938
1.4083	4.0	19980	2.0778	0.4358
1.1092	5.0	24975	2.0726	0.4608
0.8501	6.0	29970	2.1499	0.4652
0.5973	7.0	34965	2.2423	0.4586
0.4056	8.0	39960	2.3822	0.4605
0.3375	9.0	44955	2.5109	0.4564
0.2773	10.0	49950	2.6337	0.4590
0.2134	11.0	54945	2.7191	0.4698
0.1712	12.0	59940	2.8171	0.4634
0.1061	13.0	64935	2.8741	0.4687
0.1533	14.0	69930	2.9266	0.4665
0.0837	15.0	74925	2.9393	0.4657

Framework versions

• Transformers 4.27.1
• Pytorch 2.1.0.dev20230414+cu117
• Datasets 2.9.0
• Tokenizers 0.13.3