SynteractBinderHeavyWeight

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

• Loss: 0.5814
• Model Preparation Time: 0.0033
• F1: 0.7965
• Precision: 0.8854
• Recall: 0.7469
• Accuracy: 0.7469
• Mcc: 0.2478
• Auc: 0.6929

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	F1	Precision	Recall	Accuracy	Mcc	Auc
0.4572	0.2857	500	0.6190	0.0033	0.7090	0.8878	0.6300	0.6300	0.2062	0.6775
0.4046	0.5714	1000	0.6051	0.0033	0.8087	0.8835	0.7644	0.7644	0.2409	0.6826
0.3801	0.8571	1500	0.6062	0.0033	0.8109	0.8846	0.7674	0.7674	0.2472	0.6869
0.3339	1.1429	2000	0.6228	0.0033	0.8206	0.8855	0.7814	0.7814	0.2578	0.6906
0.3305	1.4286	2500	0.5848	0.0033	0.8027	0.8888	0.7547	0.7547	0.2606	0.7024
0.3133	1.7143	3000	0.6045	0.0033	0.8089	0.8869	0.764	0.764	0.2559	0.6954
0.3143	2.0	3500	0.6210	0.0033	0.8039	0.8890	0.7565	0.7565	0.2620	0.7030
0.2888	2.2857	4000	0.6206	0.0033	0.8207	0.8859	0.7814	0.7814	0.2592	0.6918
0.2871	2.5714	4500	0.6248	0.0033	0.8190	0.8885	0.7784	0.7784	0.2702	0.7022
0.2846	2.8571	5000	0.6189	0.0033	0.8145	0.8884	0.7719	0.7719	0.2664	0.7015
0.2586	3.1429	5500	0.6172	0.0033	0.8037	0.8872	0.7565	0.7565	0.2541	0.6963
0.2508	3.4286	6000	0.6283	0.0033	0.8028	0.8892	0.7548	0.7548	0.2624	0.7040
0.2532	3.7143	6500	0.6305	0.0033	0.8271	0.8873	0.7906	0.7906	0.2701	0.6970
0.2441	4.0	7000	0.6370	0.0033	0.8222	0.8861	0.7837	0.7837	0.2612	0.6925
0.2328	4.2857	7500	0.6046	0.0033	0.8094	0.8890	0.7642	0.7642	0.2656	0.7036

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1
• Datasets 3.2.0
• Tokenizers 0.21.0