roberta-mrqa-old

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

• Loss: 1.7688

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: 20
• eval_batch_size: 20
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.6529	1.0	1399	1.5408
1.2869	2.0	2798	1.6436
1.0125	3.0	4197	1.6679
0.8449	4.0	5596	1.7688

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1