132eb740f0
* wip for dbrx finetuning * add fastcore for parallel loading of sharded weights * fix dtype for load, use PartialState instead of accelerator to init process group, remove redundant wandb callback * update to use v2 of the converted model * more fixes for dbrx loras * make sure to enable fsdp activation checkpointing * fix support for 8bit loras too for dbrx * apply z3 leaf moe fix for DBRX with deepspeed * don't raise value error since child module searches could fail and be ok * revert a previous change to fix fsdp * update mistral/mistral qlora+fsdp yamls * fix qlora+fsdp quant storage type * more edge cases for qlora-fsdp * fixes for fsdp+qlora w optimizer in 8bit * add bigstral z3 config and make sure to use full_state_dict for fsdp
42 lines
1.0 KiB
JSON
42 lines
1.0 KiB
JSON
{
|
|
"zero_force_ds_cpu_optimizer": false,
|
|
"zero_allow_untested_optimizer": true,
|
|
"zero_optimization": {
|
|
"stage": 3,
|
|
"offload_optimizer": {
|
|
"device": "cpu",
|
|
"pin_memory": true
|
|
},
|
|
"offload_param": {
|
|
"device": "cpu",
|
|
"pin_memory": true
|
|
},
|
|
"overlap_comm": true,
|
|
"contiguous_gradients": true,
|
|
"sub_group_size": 0,
|
|
"reduce_bucket_size": "auto",
|
|
"stage3_prefetch_bucket_size": "auto",
|
|
"stage3_param_persistence_threshold": "auto",
|
|
"stage3_max_live_parameters": 0,
|
|
"stage3_max_reuse_distance": 0,
|
|
"stage3_gather_16bit_weights_on_model_save": true
|
|
},
|
|
"bf16": {
|
|
"enabled": true
|
|
},
|
|
"fp16": {
|
|
"enabled": "auto",
|
|
"auto_cast": false,
|
|
"loss_scale": 0,
|
|
"initial_scale_power": 32,
|
|
"loss_scale_window": 1000,
|
|
"hysteresis": 2,
|
|
"min_loss_scale": 1
|
|
},
|
|
"gradient_accumulation_steps": "auto",
|
|
"gradient_clipping": "auto",
|
|
"train_batch_size": "auto",
|
|
"train_micro_batch_size_per_gpu": "auto",
|
|
"wall_clock_breakdown": false
|
|
}
|