Fine tuning with Custom Compute Metrics
📜Get repo access at Trelis.com/ADVANCED-fine-tuning
🗝️ Get Trelis All Access (Trelis.com/All-Access)
1. Access all SEVEN Trelis Github Repos (-robotics, -vision, -evals, -fine-tuning, -inference, -voice, -time-series)
2. Support via Github Issues & Trelis’ Private Discord
3. Early access to Trelis videos via Discord
Tip: If you subscribe here on YouTube, click the bell to be notified of new vids
🛠️ (NEW) Trelis Fine-tuning Workshops: https://trelis.com/workshops-and-semi...
💡 Need Technical or Market Assistance?
Book a Consult Here: https://forms.gle/wJXVZXwioKMktjyVA
🤝 Are You a Top Developer?
Work for Trelis: https://trelis.com/jobs/
💸 Starting a New Project/Venture?
Apply for a Trelis Grant: https://trelis.com/trelis-ai-grants/
📧 Get Trelis AI Tutorials by Email
Subscribe on Substack: https://trelis.substack.com
Video Links:
Slides: https://docs.google.com/presentation/...
TIMESTAMPS:
00:00 Introduction to Tracking Loss in Model Training
00:50 Understanding Custom Metrics
01:22 Teacher Forced vs. Auto Regressive Decoding
01:32 Training vs. Inference Libraries
01:43 Options for Computing Custom Metrics
02:00 Challenges with Custom Metrics
03:44 Teacher Forced Decoding Explained
05:55 Auto Regressive Decoding Explained
08:19 Combining Training and Inference
09:22 Implementing Custom Metrics in Training
09:31 GRPO and Custom Metrics
12:11 Memory Management in Custom Metrics
15:44 Practical Demonstration: Setting Up the Environment
18:05 Loading and Training the Model
26:14 Setting Up the Training and Evaluation Dataset
26:31 Formatting the Data for Training
27:35 Custom Optimizer Setup
28:03 Loading and Printing Trainable Parameters
29:30 Fine-Tuning the Model
30:03 Custom Prediction Step and Metrics
31:42 Auto Aggressive Decoding and Evaluation
46:40 Handling Memory and GPU Utilization
49:55 Conclusion and Resources
![Nothing Suits Me Like A Suits || The Evil Within GMV [rus sub]](https://images.mixrolikus.cc/video/-kWPyySrev8)
