fine-tuning-with-trl

fine-tuning-with-trl is a skill for Claude Code from liortesta/ClawdAgent. It costs 69 tokens per session (3,079 once invoked), scanned A, a copy of trl-fine-tuning, Apache-2.0.

A toolkit for adapting language models with Hugging Face's TRL library. It supports instruction training, preference-based training, and reinforcement learning from human feedback.

In plain words
What is it for?
Use it to fine-tune models for following instructions, preferring better answers, or learning from feedback.
Why use it?
It provides ready-made training workflows for changing a model's behaviour according to examples, human preferences, or reward scores.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to fine-tune models for following instructions, preferring better answers, or learning from feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liortesta/clawdagent/trl-fine-tuning
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add liortesta/ClawdAgent --skill trl-fine-tuning
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fine-tuning-with-trl

README.md
[![agentmods](https://agentmods.dev/badge/skills/liortesta/clawdagent/trl-fine-tuning/github.svg)](https://agentmods.dev/skills/liortesta/clawdagent/trl-fine-tuning)
Your own site
<a href="https://agentmods.dev/skills/liortesta/clawdagent/trl-fine-tuning"><img src="https://agentmods.dev/badge/skills/liortesta/clawdagent/trl-fine-tuning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fine-tuning-with-trl

Your own site · 80×15
<a href="https://agentmods.dev/skills/liortesta/clawdagent/trl-fine-tuning"><img src="https://agentmods.dev/badge/skills/liortesta/clawdagent/trl-fine-tuning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,079 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 78% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.03079
Opus 5 $0.00034 $0.01540
Sonnet 5 $0.00014 $0.00616
Haiku 4.5 $0.00007 $0.00308

Measured 6d ago against content hash d68f78ad7416, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fine-tuning-with-trl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

78% identical to trl-fine-tuning — 89 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/06-post-training/trl-fine-tuning/SKILL.md · 456 lines

How it starts

The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TRL - Transformer Reinforcement Learning

Quick start

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

Installation:

pip install trl transformers datasets peft accelerate

Supervised Fine-Tuning (instruction tuning):

from trl import SFTTrainer

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

DPO (align with preferences):

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:

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:

Read the full file on GitHub · 456 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 456 lines · 69 tokens per session scan A d68f78ad7416

Subscribe to this mod's changes

fine-tuning-with-trl is a skill published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 13d ago), licensed Apache-2.0. It adds 69 tokens to every session and 3,079 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 78% identical to trl-fine-tuning, differing in 89 lines, and is treated as a copy.

Related

Other skills, from other repositories

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

davila7/claude-code-templates · 69 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

OpenLAIR/dr-claw · 69 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Orchestra-Research/AI-Research-SKILLs · 69 tokens

model_finetuning

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

vuralserhat86/antigravity-agentic-skills · 67 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

ihatesea69/HieuNghi-AI-Skills · 69 tokens

model_finetuning

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

DonggangChen/antigravity-agentic-skills · 67 tokens