metadata
library_name: transformers
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-aeslc-10-cnt-supervised-basic
results: []
bart-large-aeslc-10-cnt-supervised-basic
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5122
- Rouge1: 0.2421
- Rouge2: 0.1162
- Rougel: 0.23
- Rougelsum: 0.2305
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 4.8115 | 2.5 | 5 | 5.6510 | 0.1512 | 0.0659 | 0.1397 | 0.1397 |
| 2.9123 | 5.0 | 10 | 4.9927 | 0.232 | 0.1171 | 0.2223 | 0.2229 |
| 1.4885 | 7.5 | 15 | 5.0836 | 0.2577 | 0.1312 | 0.2487 | 0.2493 |
| 1.2593 | 10.0 | 20 | 5.1864 | 0.2555 | 0.1244 | 0.2435 | 0.244 |
| 0.9244 | 12.5 | 25 | 5.3341 | 0.2493 | 0.1196 | 0.2361 | 0.2364 |
| 0.8451 | 15.0 | 30 | 5.4642 | 0.2438 | 0.1175 | 0.2315 | 0.2318 |
| 0.9148 | 17.5 | 35 | 5.5031 | 0.2433 | 0.1167 | 0.2313 | 0.2316 |
| 0.6394 | 20.0 | 40 | 5.5122 | 0.2421 | 0.1162 | 0.23 | 0.2305 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2