Clinical STS Regression Model
Fine-tuned from cross-encoder/ms-marco-MiniLM-L6-v2 on a clinical text-pair similarity dataset.
Training config
{
"train": "./med_sts/clinicalSTS.train.txt",
"test": "./med_sts/clinicalSTS.test.txt",
"model": [
"cross-encoder/ms-marco-MiniLM-L6-v2"
],
"epochs": 20,
"batch_size": 16,
"lr": 2e-05,
"weight_decay": 0.01,
"warmup_ratio": 0.1,
"max_grad_norm": 1.0,
"dropout": 0.1,
"max_len": 256,
"seed": 42,
"patience": 5,
"output_dir": "./sts_val/ms-marco-MiniLM-L6-v2",
"wandb_project": "clinical-sts",
"hf_repo": "youssefkhalil320/ms-marco-MiniLM-L6-v2"
}
Best test Spearman ρ: 0.8130
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for youssefkhalil320/ms-marco-MiniLM-L6-v2
Base model
microsoft/MiniLM-L12-H384-uncased Quantized
cross-encoder/ms-marco-MiniLM-L12-v2 Quantized
cross-encoder/ms-marco-MiniLM-L6-v2