samuellimabraz/t5-small-ia3-finetune-tweetsumm

ia3-finetune-t5-small-tweetsumm-1724776109

This model is a fine-tuned version of google-t5/t5-small on the Andyrasika/TweetSumm-tuned dataset. It achieves the following results on the evaluation set:

• Loss: 2.4772
• Rouge1: 0.3032
• Rouge2: 0.1016
• Rougel: 0.2431
• Rougelsum: 0.2761
• Gen Len: 49.7364
• F1: 0.8624
• Precision: 0.8604
• Recall: 0.8646

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• 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	Gen Len	F1	Precision	Recall
3.074	1.0	110	2.7180	0.2578	0.07	0.2025	0.2348	49.7455	0.8554	0.8499	0.8613
2.8218	2.0	220	2.5242	0.2895	0.0902	0.2315	0.2639	49.7	0.8603	0.8578	0.863
2.5886	3.0	330	2.4772	0.3032	0.1016	0.2431	0.2761	49.7364	0.8624	0.8604	0.8646

Framework versions

• PEFT 0.12.1.dev0
• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1