bart_medical_quad_model

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

• Loss: 0.0000

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: 3.7185140364032e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 820

Training results

Training Loss	Epoch	Step	Validation Loss
0.0	0.1220	100	0.0000
0.0004	0.2439	200	0.0000
0.0	0.3659	300	0.0000
0.0004	0.4878	400	0.0000
0.0002	1.1091	500	0.0000
0.0	1.2311	600	0.0000
0.0001	1.3530	700	0.0000
0.0001	1.475	800	0.0000

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1