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-LoRA-TweetSumm-1724701402
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: Andyrasika/TweetSumm-tuned
          type: Andyrasika/TweetSumm-tuned
        metrics:
          - type: rouge
            value: 0.4387
            name: Rouge1
          - type: f1
            value: 0.8896
            name: F1
          - type: precision
            value: 0.8881
            name: Precision
          - type: recall
            value: 0.8913
            name: Recall

t5-small-LoRA-TweetSumm-1724701402

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: 2.0811
Rouge1: 0.4387
Rouge2: 0.196
Rougel: 0.3605
Rougelsum: 0.4055
Gen Len: 49.5909
F1: 0.8896
Precision: 0.8881
Recall: 0.8913

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
2.3972	1.0	110	2.1384	0.4219	0.1801	0.3545	0.3925	49.9818	0.8833	0.8806	0.8861
2.2593	2.0	220	2.0982	0.4125	0.1843	0.3448	0.3837	49.9091	0.8853	0.8822	0.8886
1.9318	3.0	330	2.0811	0.4387	0.196	0.3605	0.4055	49.5909	0.8896	0.8881	0.8913

Framework versions

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