trl-fine-tuning

Files (5)

• SKILL.md
• dpo-variants.md · references/
• online-rl.md · references/
• reward-modeling.md · references/
• sft-training.md · references/

SKILL.md (first lines)

## Kheish Compatibility

This skill is repo-local and stays inactive until explicitly activated.

When the original instructions refer to legacy tool names, use these Kheish mappings:

- `terminal` => `bash`
- `web_extract` => `web_fetch`, plus `web_search` when discovery is needed
- `search_files` => `grep_search` and `glob_search`
- `browser_*` tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitly

When the instructions mention local helper files, resolve them from `${KHEISH_SKILL_DIR}`.

# TRL - Transformer Reinforcement Learning

## Quick start

TRL provides post-training methods for aligning language models with human preferences.

**Installation**:
```bash
pip install trl transformers datasets peft accelerate
```

**Supervised Fine-Tuning** (instruction tuning):
```python
from trl import SFTTrainer

trainer = SFTTrainer(
    model="Qwen/Qwen2.5-0.5B",
    train_dataset=dataset,  # Prompt-completion pairs
)
trainer.train()
```

**DPO** (align with preferences):
```python
from trl import DPOTrainer, DPOConfig

config = DPOConfig(output_dir="model-dpo", beta=0.1)
trainer = DPOTrainer(
    model=model,
    args=config,
    train_dataset=preference_dataset,  # chosen/rejected pairs
    processing_class=tokenizer
)
trainer.train()
```

## Common workflows

### Workflow 1: Full RLHF pipeline (SFT → Reward Model → PPO)

Complete pipeline from base model to human-aligned model.

Copy this checklist:

```
RLHF Training:
- [ ] Step 1: Supervised fine-tuning (SFT)
- [ ] Step 2: Train reward model
- [ ] Step 3: PPO reinforcement learning
- [ ] Step 4: Evaluate aligned model
```

**Step 1: Supervised fine-tuning**

Train base model on instruction-following data:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from trl import SFTTrainer, SFTConfig
from datasets import load_dataset

# Load model
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B")

# Load instruction dataset
dataset = load_dataset("trl-lib/Capybara", split="train")

# Configure training
training_args = SFTConfig(
    output_dir="Qwen2.5-0.5B-SFT",
    per_device_train_batch_size=4,
    num_train_epochs=1,
    learning_rate=2e-5,
    logging_steps=10,
    save_strategy="epoch"
)

# Train
trainer = SFTTrainer(
    model=model,
    args=training_args,
    train_dataset=dataset,
    tokenizer=tokenizer
)
trainer.train()
trainer.save_model()
```

**Step 2: Train reward model**

Train model to predict human preferences:

```python
from transformers import AutoModelForSequenceClassification
from trl import RewardTrainer, RewardConfig

# Load SFT model as base
model = AutoModelForSequenceClassification.from_pretrained(
    "Qwen2.5-0.5B-SFT",
    num_labels=1  # Single reward score
)
tokenizer = AutoTokenizer.from_pretrained("Qwen2.5-0.5B-SFT")

# Load preference data (chosen/rejected pairs)
dataset = load_dataset("trl-lib/ultrafeedback_binarized", split="train")

From graniet/kheish, MIT.

More from graniet/kheish