|
--- |
|
language: |
|
- ko |
|
- zh |
|
base_model: ./zh_reduced_model |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: mbart_cycle0_ko-zh |
|
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. --> |
|
|
|
# mbart_cycle0_ko-zh |
|
|
|
This model is a fine-tuned version of [mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) on an custom dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 6.3117 |
|
- Bleu: 19.1703 |
|
- Gen Len: 14.3881 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 300 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:--------:| |
|
| No log | 8.82 | 300 | 5.4963 | 0.2892 | 127.2388 | |
|
| 8.4505 | 17.65 | 600 | 5.6784 | 18.0955 | 12.7761 | |
|
| 8.4505 | 26.47 | 900 | 5.9406 | 19.7871 | 13.6119 | |
|
| 0.4947 | 35.29 | 1200 | 6.2203 | 16.6303 | 13.209 | |
|
| 0.0447 | 44.12 | 1500 | 6.2942 | 19.9934 | 14.0448 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
