---
language:
- en
license: apache-2.0
library_name: peft
base_model: google/gemma-4-e4b-it
tags:
- gemma4
- unsloth
- lora
- qlora
- fine-tuning
- hackathon
- gemma-4-good-hackathon
- kaggle
datasets:
- mlabonne/FineTome-100k
pipeline_tag: text-generation
---

# Gemma 4 E4B Fine-Tuned with Unsloth QLoRA

**Competition:** [The Gemma 4 Good Hackathon](https://www.kaggle.com/competitions/gemma-4-good-hackathon) on Kaggle  
**Tracks:** Unsloth ($10K prize) + Impact Tracks  
**Framework:** [Unsloth](https://unsloth.ai) — 2x faster fine-tuning  
**Base Model:** [google/gemma-4-e4b-it](https://huggingface.co/google/gemma-4-e4b-it) (4B params, instruction-tuned)

## Highlights

- **99.6% training loss reduction** — from 2.916 (baseline) to **0.0115** (final)
- **5 epochs** of QLoRA fine-tuning on 10,000 high-quality samples
- **Only 2.29% of parameters trained** (146.8M / 6.4B) via rank-stabilized LoRA
- **12 hours total training** on a single NVIDIA L4 GPU (24GB)

## How to Use

### With Unsloth (Recommended)
```python
from unsloth import FastModel

model, tokenizer = FastModel.from_pretrained(
    "bradduy/Any2AnyModels",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastModel.for_inference(model)

messages = [
    {"role": "user", "content": "Explain how renewable energy helps developing communities"}
]

inputs = tokenizer.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to("cuda")

outputs = model.generate(
    input_ids=inputs,
    max_new_tokens=512,
    temperature=0.7,
    do_sample=True,
)
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
```

### With Transformers + PEFT
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-4-e4b-it",
    device_map="auto",
    load_in_4bit=True,
)
model = PeftModel.from_pretrained(base_model, "bradduy/Any2AnyModels")
tokenizer = AutoTokenizer.from_pretrained("bradduy/Any2AnyModels")
```

## Training Details

### Method

We used **Unsloth's QLoRA** implementation with **rank-stabilized LoRA (RSLoRA)** for parameter-efficient fine-tuning. The key innovation was discovering that **multi-epoch training dramatically reduces loss** with each additional pass over the data.

### Configuration

| Parameter | Value |
|-----------|-------|
| Base Model | `google/gemma-4-e4b-it` (4B params) |
| Quantization | 4-bit QLoRA via bitsandbytes |
| LoRA Rank | 64 |
| LoRA Alpha | 64 |
| RSLoRA | Enabled (rank-stabilized scaling) |
| Learning Rate | 7e-5 |
| LR Scheduler | Cosine |
| Epochs | 5 |
| Dataset Size | 10,000 samples |
| Effective Batch Size | 8 (1 × 8 grad accumulation) |
| Weight Decay | 0.01 |
| Warmup Steps | 50 |
| Total Steps | 6,250 |
| Max Seq Length | 2048 |
| Optimizer | AdamW 8-bit |
| Seed | 3407 |
| Response Masking | `train_on_responses_only` enabled |

### Dataset

- **Source:** [mlabonne/FineTome-100k](https://huggingface.co/datasets/mlabonne/FineTome-100k)
- **Samples Used:** 10,000 (first 10k)
- **Format:** Multi-turn chat conversations
- **Chat Template:** Gemma 4 native (`role: "model"`, not `"assistant"`)
- **Masking:** Only model responses contribute to loss (instruction tokens masked)

### Hardware

- **GPU:** NVIDIA L4 (24GB VRAM)
- **RAM:** 32GB
- **Training Time:** ~12 hours (with checkpoint resume)
- **GPU Memory Used:** ~14.8GB during training

## Experiment Journey

We ran **8 systematic experiments** to find the optimal configuration:

| Exp | LoRA r | Epochs | Samples | LR | Train Loss | Key Finding |
|-----|--------|--------|---------|-----|-----------|-------------|
| 01 | 16 | 0.13 | 3k | 2e-4 | 2.916 | Baseline |
| 02 | 32 | 0.24 | 5k | 2e-4 | 1.725 | Higher rank helps (+41%) |
| 03 | 64+RSLoRA | 0.20 | 10k | 2e-4 | 1.460 | RSLoRA + more data (+50%) |
| 04 | 64+RSLoRA | 0.40 | 20k | 1e-4 | ~1.05 | Lower LR improves convergence |
| 05 | 128+RSLoRA | 0.40 | 20k | 5e-5 | 1.134 | r=128 slower than r=64 |
| 06 | 64+RSLoRA | 3 | 10k | 1e-4 | ~0.30 | **Multi-epoch is transformative** |
| 07 | 128+RSLoRA | 3 | 10k | 1e-4 | ~0.59 | r=64 > r=128 for multi-epoch |
| **08** | **64+RSLoRA** | **5** | **10k** | **7e-5** | **0.0115** | **5 epochs = 99.6% reduction** |

### The Multi-Epoch Discovery

The single most impactful finding: **each additional epoch delivers a dramatic, consistent loss reduction:**

```
Epoch 1: loss ~0.90  (learning the patterns)
Epoch 2: loss ~0.60  (reinforcing knowledge)
Epoch 3: loss ~0.30  (deep memorization)
Epoch 4: loss ~0.10  (fine polishing)
Epoch 5: loss ~0.01  (near-perfect fitting)
```

This pattern was consistent across experiments 06, 07, and 08. The loss drops happen at each epoch boundary as the model sees the training data again.

### Other Key Insights

1. **r=64 with RSLoRA is the sweet spot** — r=128 converges slower and provides no benefit in multi-epoch settings
2. **Lower LR (7e-5) stabilizes long training** — higher LR (2e-4) causes instability after epoch 2
3. **`train_on_responses_only` is essential** — masks user/system tokens so the model only learns from responses
4. **Checkpoint saving every 250 steps** — long CUDA runs crash from memory fragmentation; resume from checkpoints solved this
5. **10k high-quality samples > 20k samples** for multi-epoch — quality over quantity when doing multiple passes

## Training Pipeline

Built entirely with [Unsloth](https://unsloth.ai):

```python
from unsloth import FastModel
from trl import SFTTrainer, SFTConfig
from unsloth.chat_templates import get_chat_template, train_on_responses_only

# 1. Load 4-bit quantized model
model, tokenizer = FastModel.from_pretrained(
    "unsloth/gemma-4-E4B-it-unsloth-bnb-4bit",
    max_seq_length=2048, load_in_4bit=True,
)

# 2. Apply LoRA adapters (r=64, RSLoRA)
model = FastModel.get_peft_model(model,
    finetune_vision_layers=False, finetune_language_layers=True,
    finetune_attention_modules=True, finetune_mlp_modules=True,
    r=64, lora_alpha=64, lora_dropout=0, bias="none",
    random_state=3407, use_rslora=True,
)

# 3. Setup Gemma 4 chat template
tokenizer = get_chat_template(tokenizer, chat_template="gemma-4")

# 4. Train with response-only masking
trainer = SFTTrainer(model=model, tokenizer=tokenizer, train_dataset=dataset,
    args=SFTConfig(
        per_device_train_batch_size=1, gradient_accumulation_steps=8,
        learning_rate=7e-5, num_train_epochs=5, lr_scheduler_type="cosine",
        warmup_steps=50, weight_decay=0.01, optim="adamw_8bit",
        save_strategy="steps", save_steps=250, save_total_limit=3,
    ),
)
trainer = train_on_responses_only(trainer,
    instruction_part="<|turn>user\n", response_part="<|turn>model\n",
)
trainer.train()
```

## Reproduce Training

```bash
git clone https://github.com/bradduy/Any2AnyModels
cd Any2AnyModels
pip install unsloth

python scripts/train.py \
  --model unsloth/gemma-4-E4B-it-unsloth-bnb-4bit \
  --load-4bit --lora-rank 64 --use-rslora \
  --dataset mlabonne/FineTome-100k --max-samples 10000 \
  --num-epochs 5 --learning-rate 7e-5 --grad-accum 8 \
  --weight-decay 0.01 --warmup-steps 50 --scheduler cosine \
  --save-steps 250 --save-total-limit 3
```

## Limitations

- Fine-tuned on English-only data (FineTome-100k)
- Optimized for instruction following, not domain-specific tasks
- 4B parameter model — larger models (26B, 31B) would perform better but require more VRAM
- Training loss ≠ downstream task performance; the model should be evaluated on specific benchmarks

## Acknowledgments

- **Google DeepMind** for the [Gemma 4](https://blog.google/technology/developers/gemma-4/) model family
- **[Unsloth](https://unsloth.ai)** for making QLoRA fine-tuning 2x faster and memory efficient
- **[Kaggle](https://www.kaggle.com)** for hosting the Gemma 4 Good Hackathon
- **[mlabonne](https://huggingface.co/mlabonne)** for the FineTome-100k dataset

## License

Apache 2.0 (same as Gemma 4)