Training process silently failing while generating biography

Operating System

• macOS
• Linux
• Windows

Deployment Method

• Docker
• non-Docker

CUDA Usage

• Yes
• No

Training Process Details (if applicable)

This is the step in the process where the training is stopping without issuing any error in the logs:

Here are the models I'm using, including DeepSeek for advanced behavior.

My machine is a 32GB Macbook Pro M1.

Second-Me version

0.1.0

Describe the bug

The training process just stops, but doesn't give any indication of why it's stopping (no error in the backend or frontend logs)

Current Behavior

No errors in the backend or frontend.

Expected Behavior

It would complete the training without stopping.

Reproduction Steps

Load several hundred .txt files and a large PDF doc with many journal entries. Can't share the data because it's personal and sensitive.

Possible Workaround

No response

Additional Information

No response

Link to related Github discussion or issue

No response