|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only |
|
|
tags: |
|
|
- alignment-handbook |
|
|
- trl |
|
|
- dpo |
|
|
- generated_from_trainer |
|
|
- trl |
|
|
- dpo |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- pbevan11/multilingual-constitutional-preference-pairs-revision-only |
|
|
- pbevan11/ultrafeedback_binarized_multilingual |
|
|
model-index: |
|
|
- name: Mistral-Nemo-Instruct-MCAI-SFT-DPO-revision-only |
|
|
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. --> |
|
|
|
|
|
# Mistral-Nemo-Instruct-MCAI-SFT-DPO-revision-only |
|
|
|
|
|
This model is a fine-tuned version of [pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only](https://huggingface.co/pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only) on the pbevan11/multilingual-constitutional-preference-pairs-revision-only and the pbevan11/ultrafeedback_binarized_multilingual datasets. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5140 |
|
|
- Rewards/chosen: -0.6440 |
|
|
- Rewards/rejected: -1.3117 |
|
|
- Rewards/accuracies: 0.6824 |
|
|
- Rewards/margins: 0.6678 |
|
|
- Logps/rejected: -215.4680 |
|
|
- Logps/chosen: -196.1248 |
|
|
- Logits/rejected: -0.0511 |
|
|
- Logits/chosen: -0.0322 |
|
|
|
|
|
## 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-07 |
|
|
- train_batch_size: 6 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 8 |
|
|
- total_train_batch_size: 48 |
|
|
- total_eval_batch_size: 64 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.1 |
|
|
- Pytorch 2.4.1+cu121 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.0 |
|
|
|
