mirror of
https://github.com/salesforce/CodeT5.git
synced 2024-10-01 06:35:38 -04:00
53 lines
1.4 KiB
JSON
53 lines
1.4 KiB
JSON
{
|
|
"fp16": {
|
|
"enabled": "auto",
|
|
"loss_scale": 0,
|
|
"loss_scale_window": 1000,
|
|
"initial_scale_power": 16,
|
|
"hysteresis": 2,
|
|
"min_loss_scale": 1
|
|
},
|
|
"zero_optimization": {
|
|
"stage": 2,
|
|
"offload_optimizer": {
|
|
"device": "cpu",
|
|
"pin_memory": true
|
|
},
|
|
"allgather_partitions": true,
|
|
"allgather_bucket_size": 1e8,
|
|
"overlap_comm": true,
|
|
"reduce_scatter": true,
|
|
"reduce_bucket_size": 1e8,
|
|
"contiguous_gradients": true,
|
|
"round_robin_gradients": true
|
|
},
|
|
"zero_allow_untested_optimizer": true,
|
|
"dump_state": false,
|
|
"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,
|
|
"optimizer": {
|
|
"type": "AdamW",
|
|
"params": {
|
|
"lr": "auto",
|
|
"betas": "auto",
|
|
"eps": "auto",
|
|
"weight_decay": "auto"
|
|
}
|
|
},
|
|
"scheduler": {
|
|
"type": "WarmupDecayLR",
|
|
"params": {
|
|
"last_batch_iteration": -1,
|
|
"total_num_steps": "auto",
|
|
"warmup_min_lr": 1e-5,
|
|
"warmup_max_lr": "auto",
|
|
"warmup_num_steps": "auto",
|
|
"warmup_type": "linear"
|
|
}
|
|
}
|
|
}
|