NLPClass
Collection
summarization task , fine tuning for novel chapters
•
5 items
•
Updated
bart_booksum_1
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: 3.0264
- Rouge1: 0.1795
- Rouge2: 0.0368
- Rougel: 0.1337
- Rougelsum: 0.1334
- 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: 4
- eval_batch_size: 4
- seed: 1515
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.8176 | 1.0 | 80 | 3.0712 | 0.1765 | 0.0372 | 0.1298 | 0.1299 | 20.0 |
| 3.3835 | 2.0 | 160 | 3.0365 | 0.1871 | 0.0444 | 0.1382 | 0.1382 | 20.0 |
| 3.2162 | 3.0 | 240 | 3.0281 | 0.1892 | 0.0426 | 0.1385 | 0.1383 | 20.0 |
| 3.1147 | 4.0 | 320 | 3.0264 | 0.1795 | 0.0368 | 0.1337 | 0.1334 | 20.0 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 12
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for HatimF/bart_booksum_1
Base model
facebook/bart-base