mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-31 10:12:23 +06:00

* implement gradient_accumulation_steps support in DeepSpeed integration * typo * cleanup * cleanup
46 lines
987 B
JSON
46 lines
987 B
JSON
{
|
|
"fp16": {
|
|
"enabled": true,
|
|
"loss_scale": 0,
|
|
"loss_scale_window": 1000,
|
|
"initial_scale_power": 32,
|
|
"hysteresis": 2,
|
|
"min_loss_scale": 1
|
|
},
|
|
|
|
"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
|
|
},
|
|
|
|
"zero_allow_untested_optimizer": true,
|
|
|
|
"optimizer": {
|
|
"type": "AdamW",
|
|
"params": {
|
|
"lr": 3e-5,
|
|
"betas": [0.8, 0.999],
|
|
"eps": 1e-8,
|
|
"weight_decay": 3e-7
|
|
}
|
|
},
|
|
|
|
"scheduler": {
|
|
"type": "WarmupLR",
|
|
"params": {
|
|
"warmup_min_lr": 0,
|
|
"warmup_max_lr": 3e-5,
|
|
"warmup_num_steps": 500
|
|
}
|
|
},
|
|
|
|
"steps_per_print": 2000,
|
|
"wall_clock_breakdown": false
|
|
}
|