metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: wiki_asp-written_work_4955_bart-base
results: []
wiki_asp-written_work_4955_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: 3.1703
- Rouge1: 0.1259
- Rouge2: 0.0375
- Rougel: 0.1017
- Rougelsum: 0.1018
- Gen Len: 19.446
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 | 2.12 | 500 | 3.3069 | 0.1207 | 0.0333 | 0.0979 | 0.0978 | 19.5572 |
| No log | 4.25 | 1000 | 3.2072 | 0.1199 | 0.0355 | 0.0974 | 0.0975 | 19.21 |
| No log | 6.37 | 1500 | 3.1806 | 0.1224 | 0.0358 | 0.0992 | 0.0992 | 19.2588 |
| 3.399 | 8.49 | 2000 | 3.1703 | 0.1259 | 0.0375 | 0.1017 | 0.1018 | 19.446 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2