metadata
library_name: transformers
base_model: ccdv/lsg-bart-base-16384
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: pubmed-sum
results: []
pubmed-sum
This model is a fine-tuned version of ccdv/lsg-bart-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1303
- Rouge1: 0.1396
- Rouge2: 0.0651
- Rougel: 0.1198
- Rougelsum: 0.1306
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.6342 | 0.32 | 50 | 2.7400 | 0.1174 | 0.0443 | 0.0971 | 0.1071 |
| 2.9319 | 0.64 | 100 | 2.3386 | 0.1276 | 0.0531 | 0.1071 | 0.1176 |
| 2.5759 | 0.96 | 150 | 2.2462 | 0.1313 | 0.057 | 0.111 | 0.1219 |
| 2.4678 | 1.28 | 200 | 2.1933 | 0.1308 | 0.0581 | 0.1116 | 0.1221 |
| 2.4149 | 1.6 | 250 | 2.1717 | 0.1353 | 0.0608 | 0.115 | 0.1257 |
| 2.3553 | 1.92 | 300 | 2.1303 | 0.1396 | 0.0651 | 0.1198 | 0.1306 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.19.1