t5-base-lora-finetune-tweetsumm-1759927258

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: 1.8236
• Rouge1: 0.4479
• Rouge2: 0.2102
• Rougel: 0.3774
• Rougelsum: 0.415
• Gen Len: 46.3273
• F1: 0.8903
• Precision: 0.8875
• Recall: 0.8934

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
2.106	1.0	110	1.8968	0.44	0.2049	0.3691	0.4078	49.3455	0.8867	0.8832	0.8904
1.8113	2.0	220	1.8425	0.4405	0.2078	0.3706	0.4044	47.9455	0.8895	0.887	0.8921
1.5495	3.0	330	1.8236	0.4479	0.2102	0.3774	0.415	46.3273	0.8903	0.8875	0.8934

Framework versions

• PEFT 0.17.1
• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1