metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: InstructTweetSummarizer
results: []
InstructTweetSummarizer
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3565
- Rouge1: 47.5452
- Rouge2: 25.3674
- Rougel: 36.0812
- Rougelsum: 36.2167
- Gen Len: 107.74
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: 2e-05
- train_batch_size: 5
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.5304 | 1.0 | 500 | 0.3506 | 46.2605 | 23.1881 | 33.9634 | 34.0538 | 108.25 |
| 0.2188 | 2.0 | 1000 | 0.3462 | 48.0532 | 25.4668 | 36.3198 | 36.449 | 106.76 |
| 0.1677 | 3.0 | 1500 | 0.3565 | 47.5452 | 25.3674 | 36.0812 | 36.2167 | 107.74 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0
- Datasets 2.14.7
- Tokenizers 0.14.1