samuellimabraz/t5-base-full-finetune-tweetsumm

t5-base-Full-TweetSumm-1724683206

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

• Loss: 1.8697
• Rouge1: 0.4709
• Rouge2: 0.2223
• Rougel: 0.3999
• Rougelsum: 0.4391
• Gen Len: 41.8455
• F1: 0.8952
• Precision: 0.8934
• Recall: 0.8971

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: 0.0005
• 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
2.2928	1.0	220	1.8094	0.466	0.2146	0.3912	0.4301	41.9182	0.891	0.8891	0.8931
1.2939	2.0	440	1.7929	0.4605	0.2125	0.3897	0.4259	42.0	0.8928	0.8914	0.8944
0.7227	3.0	660	1.8697	0.4709	0.2223	0.3999	0.4391	41.8455	0.8952	0.8934	0.8971

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1