|
--- |
|
license: apache-2.0 |
|
base_model: mHossain/ml_sum_v2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: ml_sum_v3 |
|
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. --> |
|
|
|
# ml_sum_v3 |
|
|
|
This model is a fine-tuned version of [mHossain/ml_sum_v2](https://huggingface.co/mHossain/ml_sum_v2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.2395 |
|
- Rouge1: 13.9684 |
|
- Rouge2: 5.8112 |
|
- Rougel: 12.261 |
|
- Rougelsum: 13.2677 |
|
- Gen Len: 19.0 |
|
|
|
## 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 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 5000 |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 312 | 2.2395 | 13.955 | 5.7928 | 12.2638 | 13.284 | 19.0 | |
|
| 2.6822 | 2.0 | 625 | 2.2395 | 13.9706 | 5.8212 | 12.2727 | 13.2752 | 19.0 | |
|
| 2.6822 | 3.0 | 937 | 2.2395 | 13.9642 | 5.8154 | 12.2569 | 13.2648 | 19.0 | |
|
| 2.658 | 3.99 | 1248 | 2.2395 | 13.9684 | 5.8112 | 12.261 | 13.2677 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
