bert-base-uncased-finetuned-squad-frozen-v1

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

bert-base-uncased-finetuned-squad

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

• Loss: 4.0178

Model description

Base model weights were frozen leaving only to finetune the last layer (qa outputs).

Training and evaluation data

Achieved EM: 8.013245033112582, F1: 15.9706088498649

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

Framework versions

• Transformers 4.15.0
• Pytorch 1.10.0+cu111
• Datasets 1.17.0
• Tokenizers 0.10.3