|
--- |
|
license: apache-2.0 |
|
base_model: youdiniplays/tl-ceb-model |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: tl-ceb-model-v2 |
|
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. --> |
|
|
|
# tl-ceb-model-v2 |
|
|
|
This model is a fine-tuned version of [youdiniplays/tl-ceb-model](https://huggingface.co/youdiniplays/tl-ceb-model) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5371 |
|
- Bleu: 3.6169 |
|
- Gen Len: 18.162 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:| |
|
| 0.6836 | 1.0 | 6547 | 0.6019 | 3.5268 | 18.224 | |
|
| 0.6358 | 2.0 | 13094 | 0.5836 | 3.5619 | 18.19 | |
|
| 0.586 | 3.0 | 19641 | 0.5585 | 3.6568 | 18.214 | |
|
| 0.5405 | 4.0 | 26188 | 0.5412 | 3.6242 | 18.174 | |
|
| 0.508 | 5.0 | 32735 | 0.5371 | 3.6169 | 18.162 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
