From dc801c07cf38b0c495686463e6ca6f871a64440e Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Tue, 27 Jan 2026 09:57:37 -0600 Subject: Add collaborativeagents module and update gitignore - Add collaborativeagents subproject with adapters, agents, and evaluation modules - Update .gitignore to exclude large binary files (.whl, .tar), wandb logs, and results Co-Authored-By: Claude Opus 4.5 --- collaborativeagents/training/ds_z3_config.json | 29 ++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 collaborativeagents/training/ds_z3_config.json (limited to 'collaborativeagents/training/ds_z3_config.json') diff --git a/collaborativeagents/training/ds_z3_config.json b/collaborativeagents/training/ds_z3_config.json new file mode 100644 index 0000000..727d015 --- /dev/null +++ b/collaborativeagents/training/ds_z3_config.json @@ -0,0 +1,29 @@ +{ + "bf16": { + "enabled": true + }, + "zero_optimization": { + "stage": 3, + "offload_optimizer": { + "device": "none" + }, + "offload_param": { + "device": "none" + }, + "overlap_comm": true, + "contiguous_gradients": true, + "sub_group_size": 1e9, + "reduce_bucket_size": "auto", + "stage3_prefetch_bucket_size": "auto", + "stage3_param_persistence_threshold": "auto", + "stage3_max_live_parameters": 1e9, + "stage3_max_reuse_distance": 1e9, + "stage3_gather_16bit_weights_on_model_save": true + }, + "gradient_accumulation_steps": "auto", + "gradient_clipping": "auto", + "steps_per_print": 10, + "train_batch_size": "auto", + "train_micro_batch_size_per_gpu": "auto", + "wall_clock_breakdown": false +} -- cgit v1.2.3