t5-simple-qg-hu

This model is a fine-tuned version of google/mt5-base on the t5_squad dataset. It achieves the following results on the evaluation set:

• Loss: 1.7546

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss
7.2425	1.35	100	2.5868
2.9755	2.71	200	1.9272
2.3029	4.06	300	1.7986
2.176	5.42	400	1.7645
2.1273	6.77	500	1.7546

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3