MeetingBank-QA-Summary

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.6280
• Rouge1: 0.1496
• Rouge2: 0.0678
• Rougel: 0.1144
• Rougelsum: 0.1126
• Generated Length: 18.6667

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Generated Length
No log	1.0	2	4.6895	0.1496	0.0678	0.1144	0.1126	18.6667
No log	2.0	4	4.6582	0.1496	0.0678	0.1144	0.1126	18.6667
No log	3.0	6	4.6280	0.1496	0.0678	0.1144	0.1126	18.6667

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Tokenizers 0.19.1