metadata

base_model: google-t5/t5-small
datasets:
  - Andyrasika/TweetSumm-tuned
library_name: peft
license: apache-2.0
metrics:
  - rouge
  - f1
  - precision
  - recall
tags:
  - generated_from_trainer
model-index:
  - name: t5-small-QLoRA-TweetSumm-1724713795
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: Andyrasika/TweetSumm-tuned
          type: Andyrasika/TweetSumm-tuned
        metrics:
          - type: rouge
            value: 0.4298
            name: Rouge1
          - type: f1
            value: 0.887
            name: F1
          - type: precision
            value: 0.8838
            name: Precision
          - type: recall
            value: 0.8904
            name: Recall

t5-small-QLoRA-TweetSumm-1724713795

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: 2.0940
Rouge1: 0.4298
Rouge2: 0.1915
Rougel: 0.3559
Rougelsum: 0.3956
Gen Len: 47.8091
F1: 0.887
Precision: 0.8838
Recall: 0.8904

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
2.3641	1.0	110	2.2019	0.4172	0.1774	0.3518	0.386	47.7636	0.8828	0.8806	0.8852
2.2228	2.0	220	2.1040	0.419	0.1789	0.3477	0.3827	48.1182	0.8846	0.882	0.8875
2.0174	3.0	330	2.0940	0.4298	0.1915	0.3559	0.3956	47.8091	0.887	0.8838	0.8904

Framework versions

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