bert-tiny-finetuned-legal-contracts-longer

This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the portion of legal_contracts dataset for 1 epoch.

Note

The model was not trained on the whole dataset which is around 9.5 GB, but only

The first 20% of train + the last 5% of train.

datasets_train = load_dataset('albertvillanova/legal_contracts' , split='train[:20%]')
datasets_validation = load_dataset('albertvillanova/legal_contracts' , split='train[-5%:]')