metadata
license: mit
base_model: facebook/bart-large-xsum
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: tech-dialogue-summarization
results: []
tech-dialogue-summarization
This model is a fine-tuned version of facebook/bart-large-xsum on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2347
- Rouge1: 28.5714
- Rouge2: 9.8361
- Rougel: 19.0476
- Rougelsum: 25.3968
- Gen Len: 21.0
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 2.5010 | 25.3968 | 9.8361 | 22.2222 | 25.3968 | 21.0 |
| No log | 2.0 | 2 | 2.5010 | 25.3968 | 9.8361 | 22.2222 | 25.3968 | 21.0 |
| No log | 3.0 | 3 | 2.2347 | 28.5714 | 9.8361 | 19.0476 | 25.3968 | 21.0 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1