|
--- |
|
license: apache-2.0 |
|
base_model: veerganesh/nvl |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: nvl-ca |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# nvl-ca |
|
|
|
This model is a fine-tuned version of [veerganesh/nvl](https://huggingface.co/veerganesh/nvl) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6535 |
|
- Rouge1: 36.3061 |
|
- Rouge2: 19.2836 |
|
- Rougel: 32.5026 |
|
- Rougelsum: 34.0495 |
|
- Gen Len: 17.64 |
|
|
|
## 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: 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.4992 | 1.0 | 50 | 1.9758 | 33.2875 | 14.2313 | 28.8961 | 30.5569 | 17.38 | |
|
| 2.1986 | 2.0 | 100 | 1.8501 | 33.5585 | 14.5244 | 29.1677 | 31.0933 | 17.74 | |
|
| 2.074 | 3.0 | 150 | 1.7800 | 33.6105 | 15.9338 | 29.4441 | 31.2427 | 17.54 | |
|
| 1.9801 | 4.0 | 200 | 1.7342 | 34.2445 | 16.941 | 29.5403 | 30.7901 | 17.62 | |
|
| 1.9218 | 5.0 | 250 | 1.7061 | 35.1758 | 17.5234 | 30.3357 | 31.8524 | 17.68 | |
|
| 1.8753 | 6.0 | 300 | 1.6854 | 34.6322 | 18.0581 | 30.5876 | 31.8437 | 17.8 | |
|
| 1.8458 | 7.0 | 350 | 1.6705 | 35.8005 | 19.1994 | 31.9266 | 33.3519 | 17.64 | |
|
| 1.8227 | 8.0 | 400 | 1.6586 | 36.5165 | 19.4833 | 32.5553 | 34.0398 | 17.56 | |
|
| 1.8097 | 9.0 | 450 | 1.6550 | 36.2766 | 19.268 | 32.4987 | 34.0117 | 17.64 | |
|
| 1.7891 | 10.0 | 500 | 1.6535 | 36.3061 | 19.2836 | 32.5026 | 34.0495 | 17.64 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
