--- license: mit --- # Moral_Instruct Have a Moral Question? Try out Moral Instruct! >[!WARNING] Please take into consideration hallucinations and don't let an LLM talk you into doing something you know is wrong. ## Introduction As LLMs see more adoption, the decisions they make to different scenarios will carry more and more weight. To better understand and nudge models into making more `moral choices`, **Moral Instruct** proposes a Supervised Fine-Tuning (SFT) which improves performance on the `moral questions` dataset by 14%. **Moral Instruct** is intended to be lightweight at ~1B parameters and 4 GB so that it can be easily be run on home computers or edge devices Given a `scenario`, `context`, `intention` and `a set of choices` this model can propose a more **moral** option, based on the popular crowd sourced benchmark. The hope is this can be used as a lightweight option to help guide a moral choice or as a part of a Mixture of Experts. The Project GitHub can be accessed [here](https://github.com/rah-ds/How_to_train_your_LLM) ## Training Data The training data was taken from [the moral stories dataset](https://huggingface.co/datasets/demelin/moral_stories) which was an [implementation](https://github.com/demelin/moral_stories) of [this paper](https://aclanthology.org/2021.emnlp-main.54/). for more information on the structure of the dataset see this [Github Readme](https://github.com/EleutherAI/lm-evaluation-harness/blob/main/lm_eval/tasks/moral_stories/README.md) The model was trained using a `train-test-holdout` validation schema summarized below A global random seed was set at 1337 at every opportunity to that the model and training are fully reproducible >[!TIP] >This random seed can be adjusted in the project `.env` file | Split | n | Comment | |---------|------|----------------------------------------------| | Train | 9600 | Shuffled | | Test | 1400 | Used to select hyper parameters | | Holdout | 50 | Evaluated general metrics, took ~ 2 min to run | The training dataset was adjusted to that the problem was a supervised learning problem where the model was supposed to choose the "right" answer. The choices were shuffled randomly so one side didn't dominate. ## Training Method > Training Method (1 paragraph): As you did in the fourth project check in, describe which method you chose for training and why you chose that method. Make note of any hyperparameter values you used so that others can reproduce your results. Given that the models were small enough to fit on a laptop and we wanted to maximize the performance on the `moral stories` benchmark, a full fine tuning approach was used. The training notebooks for the final models can be found here 1) [Falcon3-1B](https://github.com/rah-ds/How_to_train_your_LLM/blob/main/final_project/05_final_project/final_training-Falcon-1B.ipynb) 2) [gemma-3-1B-pt](https://github.com/rah-ds/How_to_train_your_LLM/blob/main/final_project/05_final_project/final_training_gemma.ipynb) 3) [GPT2-XL](https://github.com/rah-ds/How_to_train_your_LLM/blob/main/final_project/05_final_project/final_training_gpt2_xl.ipynb) The hardware the model was trained on varied but was either an NVidia A100 or A40 gpu ### Hyper Parameter Values Some Stand out values | Parameter | Value | |-------------------------------|----------| | max_steps | 10000 | | learning_rate | 0.00001 | | warmup_ratio | 0.1 | | per_device_eval_batch_size | 16 | | per_device_train_batch_size | 64 |
expand to see a full list of hyper parameters ```python TrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=True, average_tokens_across_devices=False, batch_eval_metrics=False, bf16=True, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=0, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=None, disable_tqdm=False, dispatch_batches=None, do_eval=True, do_predict=False, do_train=False, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_on_start=False, eval_steps=100, eval_strategy=IntervalStrategy.STEPS, eval_use_gather_object=False, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=1, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, greater_is_better=False, group_by_length=True, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=None, hub_strategy=HubStrategy.EVERY_SAVE, hub_token=, ignore_data_skip=False, include_for_metrics=[], include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.00001, length_column_name=length, load_best_model_at_end=True, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=./logs, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=100, logging_strategy=IntervalStrategy.STEPS, lr_scheduler_kwargs={}, lr_scheduler_type=SchedulerType.LINEAR, max_grad_norm=1.0, max_steps=10000, metric_for_best_model=loss, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=2, optim=OptimizerNames.ADAMW_TORCH, optim_args=None, optim_target_modules=None, output_dir=../scratch/trained_models/best_model, overwrite_output_dir=False, past_index=-1, per_device_eval_batch_size=16, per_device_train_batch_size=64, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=tiiuae/Falcon3-1B-Base_0.001_2000, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=1000, save_strategy=SaveStrategy.STEPS, save_total_limit=None, seed=1337, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torch_empty_cache_steps=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_liger_kernel=False, use_mps_device=False, warmup_ratio=0.1, warmup_steps=0, weight_decay=9999, ) ```
The hyper parameters were selected based on the performance on the test set and the models selected were on performance on the holdout set. ## Evaluation ### Metrics When choosing some of my Benchmark Metrics I wanted to understand how well the model understands 1) general language 2) moral/legal language. The Metrics selected were to give a balance to how much `Moral Instruct` loses in similar areas for what it gains in being able to give a moral answer to a problem. All of the questions were shuffled and had yes/no or correct or wrong answers which were evaluated. The popular Massive Multitask Language Understanding or `MMLU` benchmark offered several relevant comparisons as well as a good proxy for general utility, which are summarized below. ### Metric Definition 1. **Moral Stories**: a crowd-sourced dataset of structured narratives that describe normative and norm-divergent actions taken by individuals to accomplish certain intentions in concrete situations, and their respective consequences [paper](https://paperswithcode.com/dataset/moral-stories). It is used to evaluate models on their ability to understand and generate morally grounded narratives. Baseline 0.5 as random guessing. 2. **MMLU Moral Stories**: This metric is part of the Massive Multitask Language Understanding (MMLU) benchmark, specifically focusing on moral scenarios. It evaluates models on their ability to discern morally right and wrong actions in given scenarios [hugging face data card](https://huggingface.co/datasets/joey234/mmlu-moral_scenarios). 3. **MMLU**: a comprehensive benchmark that evaluates the capabilities of large language models across 57 subjects, including STEM fields, humanities, social sciences, and professional disciplines [wikipedia](https://en.wikipedia.org/wiki/MMLU). It tests both knowledge breadth and reasoning capabilities through multiple-choice questions. Baseline 0.25 as random guessing. 4. **MMLU Jurisprudence**:This subset of the `MMLU` benchmark focuses on legal reasoning and knowledge. It includes questions related to law and jurisprudence, testing models on their understanding of legal principles and their application [info](https://crfm.stanford.edu/2024/05/01/helm-mmlu.html). 5. **MMLU Moral Disputes**: evaluates models on their ability to navigate complex moral disputes. It includes questions that require understanding and reasoning about ethical dilemmas and moral arguments [info](https://huggingface.co/datasets/joey234/mmlu-moral_disputes/viewer). 6. **MMLU Logical Fallacies**: This subset of the `MMLU` benchmark tests models on their ability to identify and understand logical fallacies. It includes questions that require recognizing flawed reasoning and argumentation [info](https://huggingface.co/datasets/joey234/mmlu-logical_fallacies). The evaluator was in [lm_eval](https://github.com/EleutherAI/lm-evaluation-harness) and the metric scores are summarized below. The models selected were all around the same parameter size (between 1B - 1.7B) and Gemma and GPT were selected because people tend to ask moral questions to either Google or ChatGPT. The performance is summarized below: ### Before Metrics | Model | Moral Stories | MMLU Moral Stories | MMLU | MMLU Jurisprudence | MMLU Moral Disputes | MMLU Logical Fallacies | |------------|---------------|--------------------|------|--------------------|---------------------|------------------------| | Falcon3-1B | 0.66 | 0.58 | 0.56 | 0.52 | 0.45 | 0.26 | | Gemma3-1B | 0.52 | 0.34 | 0.26 | 0.22 | 0.18 | 0.16 | | GPT-xl | 0.58 | 0.34 | 0.30 | 0.28 | 0.26 | 0.26 | ### After Metrics | Model | Moral Stories | MMLU Moral Stories | MMLU | MMLU Jurisprudence | MMLU Moral Disputes | MMLU Logical Fallacies | Difference in Moral Stories | |------------|---------------|--------------------|------|--------------------|---------------------|------------------------|-----------------------------| | Falcon3-1B | 0.80 | 0.28 | 0.28 | 0.24 | 0.22 | 0.22 | 0.14 | | Gemma3-1B | 0.56 | 0.26 | 0.24 | 0.20 | 0.20 | 0.18 | 0.04 | | GPT-xl | 0.70 | 0.34 | 0.34 | 0.32 | 0.25 | 0.18 | 0.12 | The **Final Model selected** was the `Falcon3-1B`, which not only had the highest score on the `Moral Stories` Dataset, but also had the most improvement. ## Usage and Intended Uses you can follow and find the notebook for examples [here](https://github.com/rah-ds/How_to_train_your_LLM/blob/main/final_project/05_final_project/final_training-Falcon-1B.ipynb) This model is intended to be used in a way that gives background, intention, what is considered normal, and a set of two choices to choose from. The code to do so is presented below. ```python # !mkdir model-falcon # !cd model-falcon && git clone https://huggingface.co/rahkaro/Moral_Instruct && git-lfs fetch --all from transformers import AutoModelForSequenceClassification, AutoTokenizer model_name = "rahkaro/Moral_Instruct" local_path = "model-falcon/Moral_Instruct/" model = AutoModelForSequenceClassification.from_pretrained(local_path, local_files_only = True, use_safetensors=True) tokenizer = AutoTokenizer.from_pretrained(local_path, local_files_only = True) pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, # adjust if needed "return_full_text": False, "temperature": 0.0, "do_sample": False, } moral_dict = { "norm" : "it isn't right to take cookies without asking" , "situation" : "you see a bunch of cookies cooling on the window, nobody is around", "intention" : "you are really hungry and have a really big sweet tooth, nobody would mind a cookie or two gone", "moral_action" : "you knock on the door and ask for a cookie", "immoral_action" : "you just take a cookie, one cookie couldn't hurt?" } moral_prompt = f"Given the Following {d['norm']} {d['situation']} {d['intention'].} - which is the more moral choice? {[d['moral_action'], d['immoral_action']]}? Why? A: output = pipe(moral_prompt, **generation_args) print(output[0]['generated_text']) ``` ## Prompt Format where the user gives the following: * `norm` - A guideline for social conduct generally observed by most people in everyday situations. * `situation` - Setting of the story that introduces story participants and describes their environment. * `intention` - Reasonable goal that one of the story participants (the actor), wants to fulfill. * a `moral action` and an `immoral action` - two choices where one is `good` and `bad`. Or at least bad and not as bad :) read more about the dataset [here](https://github.com/EleutherAI/lm-evaluation-harness/blob/main/lm_eval/tasks/moral_stories/README.md) the general prompt code is as follows ```python moral_dict = { "norm" : "it isn't right to take cookies without asking" , "situation" : "you see a bunch of cookies cooling on the window, nobody is around", "intention" : "you are really hungry and have a really big sweet tooth, nobody would mind a cookie or two gone", "moral_action" : "you knock on the door and ask for a cookie", "immoral_action" : "you just take a cookie, one cookie couldn't hurt?" } moral_prompt = f"Given the Following {d['norm']} {d['situation']} {d['intention'].} - which is the more moral choice? {[d['moral_action'], d['immoral_action']]}? Why? A: ``` ## Expected output you would expect some of sort of string to say >you should ask for the cookie, even though you are hungry it isn't right to take without asking. The testing outside of the moral dataset questions is limited, but you should get a answer and a reason, please read the reason carefully. ## Limitations As seen by the degradation in performance on all other tasks, this model is really only suited for situations where there is a `norm`, `situation`, `intention`, and two `moral choices`. Moral Instruct is built to do well on the Moral Dataset and there has been limited testing outside of it for the scope. The model itself can hallucinate and despite the robust crowd sourced nature of the underlying dataset the data is still just a snapshot of norms and mores which are constantly changing.