metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: wiki_asp-soccer_player_8353_bart-base
results: []
wiki_asp-soccer_player_8353_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: 2.3433
- Rouge1: 0.1482
- Rouge2: 0.046
- Rougel: 0.1233
- Rougelsum: 0.1234
- Gen Len: 19.99
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 | 3.04 | 500 | 2.5513 | 0.1359 | 0.0386 | 0.1138 | 0.1139 | 19.9985 |
| No log | 6.09 | 1000 | 2.3828 | 0.1419 | 0.0427 | 0.1185 | 0.1185 | 19.9985 |
| No log | 9.13 | 1500 | 2.3433 | 0.1482 | 0.046 | 0.1233 | 0.1234 | 19.99 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2