metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
datasets:
- Andyrasika/TweetSumm-tuned
metrics:
- rouge
- f1
- precision
- recall
model-index:
- name: t5-small-Full-TweetSumm-1724699443
results:
- task:
name: Summarization
type: summarization
dataset:
name: Andyrasika/TweetSumm-tuned
type: Andyrasika/TweetSumm-tuned
metrics:
- name: Rouge1
type: rouge
value: 0.4576
- name: F1
type: f1
value: 0.8917
- name: Precision
type: precision
value: 0.8901
- name: Recall
type: recall
value: 0.8936
t5-small-Full-TweetSumm-1724699443
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: 1.9954
- Rouge1: 0.4576
- Rouge2: 0.2129
- Rougel: 0.3814
- Rougelsum: 0.4246
- Gen Len: 49.4636
- F1: 0.8917
- Precision: 0.8901
- Recall: 0.8936
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.3321 | 1.0 | 110 | 2.0722 | 0.462 | 0.2119 | 0.3832 | 0.429 | 49.4818 | 0.8916 | 0.8905 | 0.893 |
| 2.0488 | 2.0 | 220 | 2.0052 | 0.453 | 0.2025 | 0.3721 | 0.4167 | 49.5727 | 0.8912 | 0.8889 | 0.8938 |
| 1.7205 | 3.0 | 330 | 1.9954 | 0.4576 | 0.2129 | 0.3814 | 0.4246 | 49.4636 | 0.8917 | 0.8901 | 0.8936 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1