metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: wiki_asp-software_3100_bart-base
results: []
wiki_asp-software_3100_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: 3.0237
- Rouge1: 0.1523
- Rouge2: 0.0499
- Rougel: 0.1269
- Rougelsum: 0.1266
- Gen Len: 19.9987
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 | 2.51 | 500 | 3.1584 | 0.1516 | 0.0485 | 0.1263 | 0.126 | 20.0 |
| No log | 5.03 | 1000 | 3.0483 | 0.1474 | 0.0466 | 0.1226 | 0.1224 | 20.0 |
| No log | 7.54 | 1500 | 3.0237 | 0.1523 | 0.0499 | 0.1269 | 0.1266 | 19.9987 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2