metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-chat-512-seq-mini
results: []
bart-base-chat-512-seq-mini
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.4594
- Rouge1: 12.2135
- Rouge2: 1.7353
- Rougel: 8.995
- Rougelsum: 11.1148
- Gen Len: 20.0
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 | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.2467 | 1.0 | 2920 | 3.4594 | 12.2135 | 1.7353 | 8.995 | 11.1148 | 20.0 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1