|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google/mt5-small |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
model-index: |
|
|
- name: mt5-summarize-ar-en |
|
|
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. --> |
|
|
|
|
|
# mt5-summarize-ar-en |
|
|
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.9127 |
|
|
- Rouge1: 0.4091 |
|
|
- Rouge2: 0.2216 |
|
|
- Rougel: 0.3747 |
|
|
- Rougelsum: 0.3744 |
|
|
|
|
|
## 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: 0.0005 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 8 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 90 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
|
| 4.731 | 0.16 | 100 | 3.7741 | 0.3274 | 0.1592 | 0.2979 | 0.2977 | |
|
|
| 3.9076 | 0.32 | 200 | 3.3310 | 0.3424 | 0.1696 | 0.3120 | 0.3125 | |
|
|
| 3.7287 | 0.48 | 300 | 3.0822 | 0.3820 | 0.1995 | 0.3503 | 0.3501 | |
|
|
| 3.6632 | 0.64 | 400 | 3.0226 | 0.3977 | 0.2148 | 0.3621 | 0.3621 | |
|
|
| 3.3942 | 0.8 | 500 | 2.9377 | 0.4041 | 0.2151 | 0.3675 | 0.3672 | |
|
|
| 3.4731 | 0.96 | 600 | 2.9127 | 0.4091 | 0.2216 | 0.3747 | 0.3744 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.1 |
|
|
- Pytorch 2.4.0 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.0 |
|
|
|
