ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[misc] add data files (#9224)

Browse Source
This commit is contained in:
Yaowei Zheng
2025-10-02 14:02:07 +08:00
committed by GitHub
parent bcc2c1fd8f
commit a0d44c650a
27 changed files with 47563 additions and 496 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
examples/deepspeed/ds_z0_config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"zero_allow_untested_optimizer": true,
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 0,
"allgather_partitions": true,
"allgather_bucket_size": 5e8,
"overlap_comm": false,
"reduce_scatter": true,
"reduce_bucket_size": 5e8,
"contiguous_gradients": true,
"round_robin_gradients": true
}
}

28
examples/deepspeed/ds_z2_config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"zero_allow_untested_optimizer": true,
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 2,
"allgather_partitions": true,
"allgather_bucket_size": 5e8,
"overlap_comm": false,
"reduce_scatter": true,
"reduce_bucket_size": 5e8,
"contiguous_gradients": true,
"round_robin_gradients": true
}
}

32
examples/deepspeed/ds_z2_offload_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"zero_allow_untested_optimizer": true,
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 2,
"offload_optimizer": {
"device": "cpu",
"pin_memory": true
},
"allgather_partitions": true,
"allgather_bucket_size": 5e8,
"overlap_comm": false,
"reduce_scatter": true,
"reduce_bucket_size": 5e8,
"contiguous_gradients": true,
"round_robin_gradients": true
}
}

30
examples/deepspeed/ds_z3_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"zero_allow_untested_optimizer": true,
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 3,
"overlap_comm": false,
"contiguous_gradients": true,
"sub_group_size": 1e9,
"reduce_bucket_size": "auto",
"stage3_prefetch_bucket_size": "auto",
"stage3_param_persistence_threshold": "auto",
"stage3_max_live_parameters": 1e9,
"stage3_max_reuse_distance": 1e9,
"stage3_gather_16bit_weights_on_model_save": true
}
}

45
examples/deepspeed/ds_z3_fp8_config.json Normal file
View File

@@ -0,0 +1,45 @@
{
"train_micro_batch_size_per_gpu": "auto",
"gradient_clipping": "auto",
"zero_allow_untested_optimizer": true,
"zero_force_ds_cpu_optimizer": true,
"fp16": {
"enabled": false,
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 3,
"offload_optimizer": {
"device": "cpu",
"pin_memory": false
},
"overlap_comm": false,
"contiguous_gradients": true,
"sub_group_size": 1000000000,
"reduce_bucket_size": 12845056,
"stage3_prefetch_bucket_size": 11560550,
"stage3_param_persistence_threshold": 35840,
"stage3_max_live_parameters": 1000000000,
"stage3_max_reuse_distance": 1000000000,
"stage3_gather_16bit_weights_on_model_save": true
},
"steps_per_print": 10000000,
"gradient_accumulation_steps": "auto",
"comms_config": {
"verbose": false
},
"monitor_config": {
"enabled": true,
"tag": "DeepSpeedMonitor",
"csv_monitor": {
"enabled": false
}
}
}

38
examples/deepspeed/ds_z3_offload_config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"zero_allow_untested_optimizer": true,
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 3,
"offload_optimizer": {
"device": "cpu",
"pin_memory": true
},
"offload_param": {
"device": "cpu",
"pin_memory": true
},
"overlap_comm": false,
"contiguous_gradients": true,
"sub_group_size": 1e9,
"reduce_bucket_size": "auto",
"stage3_prefetch_bucket_size": "auto",
"stage3_param_persistence_threshold": "auto",
"stage3_max_live_parameters": 1e9,
"stage3_max_reuse_distance": 1e9,
"stage3_gather_16bit_weights_on_model_save": true
}
}