drug-interaction-checker

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6834
• Accuracy: 0.72

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	9	1.5738	0.32
1.5959	2.0	18	1.5481	0.32
1.5782	3.0	27	1.5276	0.32
1.5468	4.0	36	1.4967	0.32
1.4984	5.0	45	1.4058	0.32
1.4391	6.0	54	1.2875	0.56
1.3375	7.0	63	1.1871	0.6
1.1390	8.0	72	1.0902	0.76
1.0902	9.0	81	1.0129	0.72
0.9612	10.0	90	0.9060	0.72
0.9612	11.0	99	0.8581	0.76
0.9075	12.0	108	0.7975	0.76
0.7749	13.0	117	0.7692	0.76
0.7671	14.0	126	0.7394	0.76
0.7577	15.0	135	0.7459	0.72
0.7183	16.0	144	0.6945	0.72
0.7016	17.0	153	0.6798	0.72
0.6367	18.0	162	0.6998	0.72
0.6539	19.0	171	0.6883	0.72
0.6334	20.0	180	0.6834	0.72

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2