metadata
license: apache-2.0
base_model: google-t5/t5-base
tags:
- generated_from_trainer
datasets:
- Andyrasika/TweetSumm-tuned
metrics:
- rouge
- f1
- precision
- recall
model-index:
- name: t5-base-Full-TweetSumm-1724683206
results:
- task:
name: Summarization
type: summarization
dataset:
name: Andyrasika/TweetSumm-tuned
type: Andyrasika/TweetSumm-tuned
metrics:
- name: Rouge1
type: rouge
value: 0.4709
- name: F1
type: f1
value: 0.8952
- name: Precision
type: precision
value: 0.8934
- name: Recall
type: recall
value: 0.8971
t5-base-Full-TweetSumm-1724683206
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: 1.8697
- Rouge1: 0.4709
- Rouge2: 0.2223
- Rougel: 0.3999
- Rougelsum: 0.4391
- Gen Len: 41.8455
- F1: 0.8952
- Precision: 0.8934
- Recall: 0.8971
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.2928 | 1.0 | 220 | 1.8094 | 0.466 | 0.2146 | 0.3912 | 0.4301 | 41.9182 | 0.891 | 0.8891 | 0.8931 |
| 1.2939 | 2.0 | 440 | 1.7929 | 0.4605 | 0.2125 | 0.3897 | 0.4259 | 42.0 | 0.8928 | 0.8914 | 0.8944 |
| 0.7227 | 3.0 | 660 | 1.8697 | 0.4709 | 0.2223 | 0.3999 | 0.4391 | 41.8455 | 0.8952 | 0.8934 | 0.8971 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1