tinybert-6l-768d-squad2-finetuned-SRH-v2

This model is a fine-tuned version of deepset/tinybert-6l-768d-squad2 on the srh_test66 dataset. It achieves the following results on the evaluation set:

• Loss: 1.7136

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
4.0123	1.0	43	1.7703
1.3653	2.0	86	1.7254
1.5558	3.0	129	1.7136

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2