metadata
base_model: facebook/bart-base
library_name: peft
license: apache-2.0
metrics:
- rouge
tags:
- generated_from_trainer
model-index:
- name: bart-base-summarization-medical-48
results: []
bart-base-summarization-medical-48
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1260
- Rouge1: 0.4187
- Rouge2: 0.2233
- Rougel: 0.3553
- Rougelsum: 0.3545
- Gen Len: 18.201
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 48
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.6968 | 1.0 | 1250 | 2.1990 | 0.4139 | 0.2206 | 0.353 | 0.3525 | 17.88 |
| 2.6029 | 2.0 | 2500 | 2.1650 | 0.415 | 0.2192 | 0.351 | 0.3503 | 18.142 |
| 2.5682 | 3.0 | 3750 | 2.1438 | 0.4162 | 0.2188 | 0.35 | 0.3495 | 18.151 |
| 2.5281 | 4.0 | 5000 | 2.1297 | 0.4189 | 0.223 | 0.3559 | 0.3553 | 18.287 |
| 2.5228 | 5.0 | 6250 | 2.1269 | 0.4175 | 0.2228 | 0.3551 | 0.3545 | 18.157 |
| 2.542 | 6.0 | 7500 | 2.1260 | 0.4187 | 0.2233 | 0.3553 | 0.3545 | 18.201 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1