la-min/t5-finetune-health

---

license: apache-2.0 base_model: google/flan-t5-base tags:

• generated_from_trainer datasets:
• medical_q&a

---

flan-t5-base-finetuned-medical_q&a

This model is a fine-tuned version of google/flan-t5-base on the medical_q&a dataset.

Model description

When using the model input question, please add "Please answer this question:"

Training hyperparameters

The following hyperparameters were used during training:

• L_RATE = 3e-4
• BATCH_SIZE = 3
• PER_DEVICE_EVAL_BATCH = 4
• WEIGHT_DECAY = 0.01
• SAVE_TOTAL_LIM = 3
• NUM_EPOCHS = 3

Training results

Training Loss	Epoch	Validation Loss
1.757200	1.0	1.453026
1.549100	2.0	1.313304
1.474500	3.0	1.264468

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.0
• Tokenizers 0.13.3