adeobootpin

Can I train with freeze_mhra=True? (in config_7b_stage1.py) In other words can I totally freeze the visual encoder and train a model that works? Thanks

Unable to train SmoLlm model

1

I tried to kick off SFT of SmoLlm (ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3.yaml scripts/run_sft.py recipes/smollm/sft/config.yaml) Something appears to be broken when generating the training sets. See below for the tail...

[Bug] TC-IDM-10.3 is failing

1

### Describe the bug When I run the TC-IDM-10.3 in the Matter Test Harness, I get this failure: "Problem: ProblemSeverity.ERROR test_name: IDM-10.3 location: Endpoint: 0, Cluster: 29 (0x1d) Descriptor Attribute:65533...