base_model: microsoft/Phi-4-mini-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

# 1. Dataset Configuration
datasets:
  - path: DannyAI/African-History-QA-Dataset
    split: train
    type: alpaca_chat.load_qa
    system_prompt: "You are a helpful AI assistant specialised in African history."
test_datasets:
  - path: DannyAI/African-History-QA-Dataset
    split: validation
    type: alpaca_chat.load_qa
    system_prompt: "You are a helpful AI assistant specialised in African history."

# 2. Chat Configuration
chat_template: tokenizer_default
train_on_inputs: false

# 3. Batch Size Configuration
micro_batch_size: 2
gradient_accumulation_steps: 4 # Axolotl will calculate: total_batch_size = 2 * 4 * 1 GPU = 8

# 4. LoRA Configuration
adapter: lora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules: [q_proj, v_proj, k_proj, o_proj]

# 5. Hardware & Efficiency
sequence_len: 2048
sample_packing: true
eval_sample_packing: false 
pad_to_sequence_len: true
bf16: true
fp16: false

# 6. Training Duration
max_steps: 650  
# removed
# num_epochs: 
warmup_steps: 20
learning_rate: 0.00002
optimizer: adamw_torch 
lr_scheduler: cosine

# 7. Logging & DeepSpeed
deepspeed: using_axolotl/ds_config_2.json 
wandb_project: phi4_african_history
wandb_name: phi4_axolotl_stage2

eval_strategy: steps
eval_steps: 50
save_strategy: steps
save_steps: 100
logging_steps: 5

# 8. Public Hugging Face Hub Upload
hub_model_id: DannyAI/phi4_african_history_lora_ds2_axolotl
push_adapter_to_hub: true
hub_private_repo: false

Model Card for Model ID

This is a LoRA fine-tuned version of microsoft/Phi-4-mini-instruct for African History using the DannyAI/African-History-QA-Dataset dataset. It achieves a loss value of 1.7608 on the validation set

Model Details

Model Description

Developed by: Daniel Ihenacho
Funded by: Daniel Ihenacho
Shared by: Daniel Ihenacho
Model type: Text Generation
Language(s) (NLP): English
License: mit
Finetuned from model: microsoft/Phi-4-mini-instruct

Uses

This can be used for QA datasets about African History

Out-of-Scope Use

Can be used beyond African History but should not.

How to Get Started with the Model

python

from transformers import pipeline
from transformers import (
    AutoTokenizer, 
    AutoModelForCausalLM)
from peft import PeftModel


model_id = "microsoft/Phi-4-mini-instruct"

tokeniser = AutoTokenizer.from_pretrained(model_id)

# load base model
model  = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map = "auto",
    torch_dtype = torch.bfloat16,
    trust_remote_code = False
)

# Load the fine-tuned LoRA model
lora_id = "DannyAI/phi4_african_history_lora_ds2_axolotl"
lora_model = PeftModel.from_pretrained(
    model,lora_id
)

generator = pipeline(
    "text-generation",
    model=lora_model,
    tokenizer=tokeniser,
)
question = "What is the significance of African feminist scholarly activism in contemporary resistance movements?"
def generate_answer(question)->str:
    """Generates an answer for the given question using the fine-tuned LoRA model.
    """
    messages = [
        {"role": "system", "content": "You are a helpful AI assistant specialised in African history which gives concise answers to questions asked."},
        {"role": "user", "content": question}
    ]
    
    output = generator(
        messages, 
        max_new_tokens=2048, 
        temperature=0.1, 
        do_sample=False,
        return_full_text=False
    )
    return output[0]['generated_text'].strip()

# Example output
African feminist scholarly activism is significant in contemporary resistance movements as it provides a critical framework for understanding and addressing the specific challenges faced by African women in the context of global capitalism, neocolonialism, and patriarchal structures.

Training Details

Training results

Training Loss	Epoch	Step	Validation Loss	Ppl	Active (gib)	Allocated (gib)	Reserved (gib)
No log	0	0	2.1261	8.3822	14.81	14.81	15.32
5.5167	3.8627	50	2.1056	8.2118	14.82	14.82	31.8
4.5059	7.7059	100	2.0382	7.6764	14.82	14.82	31.82
3.8251	11.5490	150	1.9809	7.2491	14.82	14.82	31.82
3.4152	15.3922	200	1.9343	6.9193	14.82	14.82	31.82
3.1617	19.2353	250	1.8731	6.5085	14.82	14.82	31.82
2.9075	23.0784	300	1.8246	6.2002	14.82	14.82	31.82
2.8267	26.9412	350	1.7945	6.0164	14.82	14.82	31.82
2.7239	30.7843	400	1.7794	5.9262	14.82	14.82	31.82
2.7275	34.6275	450	1.7697	5.8690	14.82	14.82	31.82
2.6912	38.4706	500	1.7634	5.8325	14.82	14.82	31.82
2.6632	42.3137	550	1.7618	5.8227	14.82	14.82	31.82
2.6604	46.1569	600	1.7609	5.8179	14.82	14.82	31.82
2.6795	50.0	650	1.7608	5.8168	14.82	14.82	31.82

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
training_steps: 650

Lora Configuration

r: 8
lora_alpha: 16
target_modules: ["q_proj", "v_proj", "k_proj", "o_proj"]
lora_dropout: 0.05 # dataset is small, hence a low dropout value
bias: "none"
task_type: "CAUSAL_LM"

Evaluation

Metrics

Models	Bert Score	TinyMMLU	TinyTrufulQA
Base model	0.88868	0.6837	0.49745
Fine tuned Model	0.88872	0.67371	0.46877

Compute Infrastructure

Runpod.

Hardware

Runpod A40 GPU instance

Framework versions

PEFT 0.18.1
Transformers 4.57.6
Pytorch 2.9.1+cu128
Datasets 4.5.0
Tokenizers 0.22.2

Citation

If you use this dataset, please cite:

@Model{
Ihenacho2026phi4_african_history_lora_ds2_axolotl,
  author    = {Daniel Ihenacho},
  title     = {phi4_african_history_lora_ds2_axolotl},
  year      = {2026},
  publisher = {Hugging Face Models},
  url       = {https://huggingface.co/DannyAI/phi4_african_history_lora_ds2_axolotl},
  urldate   = {2026-01-27},
}

Model Card Authors

Daniel Ihenacho

DannyAI/phi4_african_history_lora_ds2_axolotl