|
--- |
|
license: apache-2.0 |
|
base_model: DAMO-NLP-MT/polylm-1.7b |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: polylm_1.7b_ft_alpaca_clean_dutch |
|
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. --> |
|
|
|
# polylm_1.7b_ft_alpaca_clean_dutch |
|
|
|
This model is a fine-tuned version of [DAMO-NLP-MT/polylm-1.7b](https://huggingface.co/DAMO-NLP-MT/polylm-1.7b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8483 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 64 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.1248 | 0.16 | 128 | 2.1129 | |
|
| 2.0512 | 0.33 | 256 | 2.0347 | |
|
| 1.9983 | 0.49 | 384 | 1.9948 | |
|
| 1.9557 | 0.66 | 512 | 1.9655 | |
|
| 1.9583 | 0.82 | 640 | 1.9386 | |
|
| 1.916 | 0.99 | 768 | 1.9177 | |
|
| 1.8671 | 1.15 | 896 | 1.9019 | |
|
| 1.8626 | 1.32 | 1024 | 1.8885 | |
|
| 1.8321 | 1.48 | 1152 | 1.8762 | |
|
| 1.8596 | 1.65 | 1280 | 1.8631 | |
|
| 1.843 | 1.81 | 1408 | 1.8539 | |
|
| 1.8333 | 1.98 | 1536 | 1.8483 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
