wehub-resource-sync
e06fe8e8c6
Secret Leaks / trufflehog (push) Failing after 1s
Build documentation / build (push) Failing after 1s
Build documentation / build_other_lang (push) Failing after 0s
CodeQL Security Analysis / CodeQL Analysis (push) Failing after 0s
PR CI / pr-ci (push) Failing after 1s
Slow tests on important models (on Push - A10) / Get all modified files (push) Failing after 1s
Slow tests on important models (on Push - A10) / Model CI (push) Has been skipped
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
33 lines
699 B
JSON
33 lines
699 B
JSON
{
|
|
"fp16": {
|
|
"enabled": "auto"
|
|
},
|
|
"bf16": {
|
|
"enabled": "auto"
|
|
},
|
|
"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
|
|
},
|
|
"gradient_accumulation_steps": "auto",
|
|
"gradient_clipping": "auto",
|
|
"train_batch_size": "auto",
|
|
"train_micro_batch_size_per_gpu": "auto"
|
|
}
|