metadata
license: apache-2.0
base_model: GuysTrans/bart-base-re-attention-seq-512
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-re-attention-seq-512
results: []
bart-base-re-attention-seq-512
This model is a fine-tuned version of GuysTrans/bart-base-re-attention-seq-512 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0593
- Rouge1: 36.619
- Rouge2: 28.9914
- Rougel: 35.1444
- Rougelsum: 36.1192
- Bleu-1: 12.5425
- Bleu-2: 11.1852
- Bleu-3: 10.5404
- Bleu-4: 10.1255
- Gen Len: 25.9532
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu-1 | Bleu-2 | Bleu-3 | Bleu-4 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.1743 | 1.0 | 18247 | 1.0593 | 36.619 | 28.9914 | 35.1444 | 36.1192 | 12.5425 | 11.1852 | 10.5404 | 10.1255 | 25.9532 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3