Files
deepspeedai--deepspeed/tests/model/Megatron_GPT2/ds_config_func_bs8_zero2.json
T
2026-07-13 13:18:33 +08:00

24 lines
512 B
JSON
Executable File

{
"train_batch_size": 8,
"gradient_accumulation_steps": 1,
"steps_per_print": 1,
"zero_optimization": {
"stage": 2,
"reduce_bucket_size": 7000000,
"allgather_bucket_size": 7000000,
"reduce_scatter": true
},
"gradient_clipping": 1.0,
"fp16": {
"enabled": true,
"loss_scale": 0,
"loss_scale_window": 1000,
"hysteresis": 2,
"min_loss_scale": 1
},
"activation_checkpointing": {
"partition_activations": true,
"contiguous_memory_optimization": true
}
}