metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: wiki_asp-soccer_player_7726_bart-base
results: []
wiki_asp-soccer_player_7726_bart-base
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2561
- Rouge1: 0.0369
- Rouge2: 0.0124
- Rougel: 0.0314
- Rougelsum: 0.0316
- Gen Len: 7.0433
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.82 | 500 | 2.5528 | 0.0155 | 0.0047 | 0.0125 | 0.0125 | 4.4707 |
| No log | 3.64 | 1000 | 2.3699 | 0.0285 | 0.0099 | 0.0239 | 0.0241 | 5.6349 |
| No log | 5.45 | 1500 | 2.3079 | 0.0155 | 0.0055 | 0.0131 | 0.0132 | 4.4819 |
| 2.6218 | 7.27 | 2000 | 2.2763 | 0.0319 | 0.0107 | 0.0272 | 0.0273 | 6.2228 |
| 2.6218 | 9.09 | 2500 | 2.2561 | 0.0369 | 0.0124 | 0.0314 | 0.0316 | 7.0433 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2