metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-transcript-summarizer
results: []
bart-large-cnn-transcript-summarizer
This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3148
- Rouge1: 40.9221
- Rouge2: 20.8127
- Rougel: 31.264
- Rougelsum: 37.9164
- Gen Len: 60.044
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.3091 | 1.0 | 3683 | 0.3163 | 40.7512 | 20.5582 | 31.1674 | 38.0718 | 60.0978 |
| 0.2138 | 2.0 | 7366 | 0.3148 | 40.9221 | 20.8127 | 31.264 | 37.9164 | 60.044 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 3.6.0
- Tokenizers 0.15.2