qwerrwe / ds_config.json
winglian's picture
deepspeed doesn't work with flash-attn, and the gpu savings w flash attn are better than the deepspeed headaches
d1aed4c
raw
history blame
844 Bytes
{
"bf16": {
"enabled": "auto"
},
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"scheduler": {
"type": "WarmupLR",
"params": {
"warmup_min_lr": "auto",
"warmup_max_lr": "auto",
"warmup_num_steps": "auto"
}
},
"zero_optimization": {
"stage": 2,
"overlap_comm": true,
"allgather_partitions": true,
"allgather_bucket_size": 5e8,
"contiguous_gradients": true,
"reduce_bucket_size": "auto",
"reduce_scatter": true
},
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"steps_per_print": 5,
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false,
"round_robin_gradients": true
}