|
--- |
|
license: apache-2.0 |
|
base_model: jhpassion0621/kp-mt5-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: kp-mt5-large |
|
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. --> |
|
|
|
# kp-mt5-large |
|
|
|
This model is a fine-tuned version of [jhpassion0621/kp-mt5-large](https://huggingface.co/jhpassion0621/kp-mt5-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5586 |
|
- Bleu: 43.3983 |
|
- Gen Len: 45.6585 |
|
|
|
## 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: 2.59e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Bleu | Gen Len | Validation Loss | |
|
|:-------------:|:-----:|:------:|:-------:|:-------:|:---------------:| |
|
| 1.0364 | 0.29 | 17000 | 32.5573 | 44.7582 | 0.8278 | |
|
| 0.8819 | 0.58 | 34000 | 37.1161 | 45.0568 | 0.7062 | |
|
| 0.7731 | 0.87 | 51000 | 40.329 | 45.7359 | 0.6188 | |
|
| 0.7339 | 1.16 | 68000 | 41.7643 | 45.8618 | 0.5866 | |
|
| 0.7093 | 1.45 | 85000 | 42.6878 | 45.5649 | 0.5657 | |
|
| 0.6818 | 1.74 | 102000 | 43.2023 | 45.7701 | 0.5609 | |
|
| 0.6739 | 2.00 | 117444 | 43.3983 | 45.6585 | 0.5586 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
|
|
