README.md

metadata

library_name: peft
license: apache-2.0
base_model: google-t5/t5-base
tags:
  - base_model:adapter:google-t5/t5-base
  - lora
  - transformers
datasets:
  - Andyrasika/TweetSumm-tuned
metrics:
  - rouge
  - f1
  - precision
  - recall
model-index:
  - name: t5-base-lora-finetune-tweetsumm-1760075742
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: Andyrasika/TweetSumm-tuned
          type: Andyrasika/TweetSumm-tuned
        metrics:
          - type: rouge
            value: 0.4407
            name: Rouge1
          - type: f1
            value: 0.8888
            name: F1
          - type: precision
            value: 0.8854
            name: Precision
          - type: recall
            value: 0.8924
            name: Recall

t5-base-lora-finetune-tweetsumm-1760075742

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: 1.8115
• Rouge1: 0.4407
• Rouge2: 0.2025
• Rougel: 0.368
• Rougelsum: 0.4049
• Gen Len: 47.8545
• F1: 0.8888
• Precision: 0.8854
• Recall: 0.8924

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
2.1023	1.0	110	1.8780	0.424	0.1972	0.3628	0.3926	48.7	0.8843	0.8815	0.8873
1.7351	2.0	220	1.8109	0.4494	0.2109	0.3799	0.4135	49.1909	0.8907	0.8879	0.8937
1.5234	3.0	330	1.8115	0.4407	0.2025	0.368	0.4049	47.8545	0.8888	0.8854	0.8924

Framework versions

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