Peiyuan Zhang
8ec82cbc37
Delete Open Sora Plan Modeling amend log validation Change name to fast video Remove OSP modeling clean up name changing remove files Deleted unnecessary files commit first commit first training ok Update generate_synthetic.sh and deepspeed_zero2_config.yaml 14 debug overfitting .... debugging .. Debug successful! Add zero3 OK update optimizer load small bug random seed args sp enable & still has bug rename update inference sp code / can run / still has bug / don't output normal mp4 switch to deepspeed dummyoptim fix some bugs; still output green SP inference done! fix typos in readme and latent dataset debug file
44 lines
1.1 KiB
JSON
44 lines
1.1 KiB
JSON
{
|
|
"fp16": {
|
|
"enabled": false,
|
|
"loss_scale": 0,
|
|
"loss_scale_window": 1000,
|
|
"initial_scale_power": 16,
|
|
"hysteresis": 2,
|
|
"min_loss_scale": 1
|
|
},
|
|
"bf16": {
|
|
"enabled": "auto"
|
|
},
|
|
"optimizer": {
|
|
"type": "AdamW",
|
|
"params": {
|
|
"lr": "auto",
|
|
"betas": [0.9, 0.999],
|
|
"eps": 1e-8,
|
|
"weight_decay": "auto"
|
|
}
|
|
},
|
|
"scheduler": {
|
|
"type": "WarmupCosineLR",
|
|
"params": {
|
|
"warmup_min_ratio": 0.0,
|
|
"cos_min_ratio": 0.1,
|
|
"warmup_type": "linear",
|
|
"warmup_num_steps": "auto",
|
|
"total_num_steps": "auto"
|
|
}
|
|
},
|
|
"communication_data_type": "fp32",
|
|
"gradient_clipping": 1.0,
|
|
"train_micro_batch_size_per_gpu": "auto",
|
|
"train_batch_size": "auto",
|
|
"gradient_accumulation_steps": "auto",
|
|
"zero_optimization": {
|
|
"stage": 2,
|
|
"overlap_comm": true,
|
|
"contiguous_gradients": true,
|
|
"sub_group_size": 1e9,
|
|
"reduce_bucket_size": 5e8
|
|
}
|
|
} |