distilbert-base-uncased-finetuned-PubmedQA

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

• Loss: 4.2957

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	21	4.6513
No log	2.0	42	4.1809
No log	3.0	63	4.1888
No log	4.0	84	4.0779
No log	5.0	105	4.1221
No log	6.0	126	4.1381
No log	7.0	147	4.0619
No log	8.0	168	4.1242
No log	9.0	189	4.1044
No log	10.0	210	4.1699
No log	11.0	231	4.1761
No log	12.0	252	4.3132
No log	13.0	273	4.2233
No log	14.0	294	4.3036
No log	15.0	315	4.2894
No log	16.0	336	4.3075
No log	17.0	357	4.3120
No log	18.0	378	4.2841
No log	19.0	399	4.3161
No log	20.0	420	4.2957

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2