license: mit
base_model: BramVanroy/fietje-2b-instruct
tags:
- trl
- fietje
- alignment-handbook
- dpo
datasets:
- BramVanroy/ultra_feedback_dutch_cleaned
- BramVanroy/orca_dpo_pairs_dutch_cleaned
model-index:
- name: fietje-2b-chat
results: []
pipeline_tag: text-generation
inference: false
language:
- nl
Fietje 2B Chat
An open and efficient LLM for Dutch👱♀️ Base version - 🤖 Instruct version - 💬 Chat version (this one) - 🚀 GGUF of Chat
This is the chat version of Fietje, a DPO-tuned (aligned) continuation on the instruct version. Fietje is an adapated version of microsoft/phi-2, tailored to Dutch text generation by training on 28B tokens. It is small and efficient with a size of 2.7 billion parameters while performing almost on par with more powerful Dutch LLMs of twice its size like GEITje 7B Ultra.
A thorough description of the creation and evaluation of Fietje as well as usage examples are available in this Github repository.
Intended uses & limitations
The same limitations as phi-2, and LLMs in general, apply here. LLMs hallucinate, make mistakes, and should not be trusted. Use at your own risk!
Training and evaluation data
Fietje 2B instruct was finetuned from the instruct model on the following datasets. Number of training samples per dataset given in brackets, totalling 18,653 samples.
- BramVanroy/ultra_feedback_dutch_cleaned subset
dpo_hq: a cleaned version of BramVanroy/ultra_feedback_dutch (9186) - BramVanroy/orca_dpo_pairs_dutch_cleaned subset
dpo_all: a cleaned version of BramVanroy/orca_dpo_pairs_dutch (9467)
A lot of different learning rates, beta, en batch sizes were investigated in search of a converging combination. You can find them all in the W&B runs.
Training procedure
I am thankful to the Flemish Supercomputer Center (VSC) for providing the computational power to accomplish this project. Accounting for waiting for jobs, training a single run took around nine hours on one A100 80GB.
Training was done with the wonderful alignment-handbook, using DeepSpeed as a back-end. Exact training recipes and SLURM script are given in the Github repository.
Training hyperparameters
The following hyperparameters were used during training:
- beta: 0.2
- learning_rate: 2e-06
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2515 | 1.0 | 1166 | 0.2842 | -1.1549 | -3.6363 | 0.8867 | 2.4815 | -657.6813 | -451.3364 | -1.2868 | -1.3528 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2