* adding Z-inf * revamp config process * up version requirement * wip * massive rewrite * cleanup * cleanup * Apply suggestions from code review Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * consistent json commas * act on suggestions * leave this feature for 0.3.16 * style Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
48 lines
1.1 KiB
JSON
48 lines
1.1 KiB
JSON
{
|
|
"fp16": {
|
|
"enabled": "auto",
|
|
"loss_scale": 0,
|
|
"loss_scale_window": 1000,
|
|
"initial_scale_power": 16,
|
|
"hysteresis": 2,
|
|
"min_loss_scale": 1
|
|
},
|
|
|
|
"optimizer": {
|
|
"type": "AdamW",
|
|
"params": {
|
|
"lr": "auto",
|
|
"betas": "auto",
|
|
"eps": "auto",
|
|
"weight_decay": "auto"
|
|
}
|
|
},
|
|
|
|
"scheduler": {
|
|
"type": "WarmupLR",
|
|
"params": {
|
|
"warmup_min_lr": "auto",
|
|
"warmup_max_lr": "auto",
|
|
"warmup_num_steps": "auto"
|
|
}
|
|
},
|
|
|
|
"zero_optimization": {
|
|
"stage": 2,
|
|
"allgather_partitions": true,
|
|
"allgather_bucket_size": 2e8,
|
|
"overlap_comm": true,
|
|
"reduce_scatter": true,
|
|
"reduce_bucket_size": 2e8,
|
|
"contiguous_gradients": true,
|
|
"cpu_offload": true
|
|
},
|
|
|
|
"gradient_accumulation_steps": "auto",
|
|
"gradient_clipping": "auto",
|
|
"steps_per_print": 2000,
|
|
"train_batch_size": "auto",
|
|
"train_micro_batch_size_per_gpu": "auto",
|
|
"wall_clock_breakdown": false
|
|
}
|