metadata
license: apache-2.0
base_model: roofdancer/thesis-bart-finetuned
tags:
- generated_from_trainer
datasets:
- wcep-10
metrics:
- rouge
model-index:
- name: thesis-bart-finetuned-on-original-wcep-500
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: wcep-10
type: wcep-10
config: roberta
split: validation
args: roberta
metrics:
- name: Rouge1
type: rouge
value: 35.0169
thesis-bart-finetuned-on-original-wcep-500
This model is a fine-tuned version of roofdancer/thesis-bart-finetuned on the wcep-10 dataset. It achieves the following results on the evaluation set:
- Loss: 2.1217
- Rouge1: 35.0169
- Rouge2: 14.4075
- Rougel: 24.4949
- Rougelsum: 28.2941
- Gen Len: 71.6902
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 32 | 2.1140 | 34.7405 | 14.1273 | 24.143 | 28.0926 | 71.6676 |
| No log | 2.0 | 64 | 2.1159 | 35.1873 | 14.5677 | 24.6163 | 28.2788 | 71.5127 |
| No log | 3.0 | 96 | 2.1217 | 35.0169 | 14.4075 | 24.4949 | 28.2941 | 71.6902 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2