初始化项目,由ModelHub XC社区提供模型
Model: DCAgent/g1_gptlong_top8_32b Source: Original Platform
This commit is contained in:
15
training_configs/sft_config.json
Normal file
15
training_configs/sft_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"job_name": "g1_gptlong_top8_32b__Qwen3-8B",
|
||||
"train_config_path": "/e/scratch/jureap59/raoof1/sft_experiments/g1_gptlong_top8_32b/configs/g1_gptlong_top8_32b__Qwen3-8B_train_config.yaml",
|
||||
"experiments_dir": "/e/scratch/jureap59/raoof1/sft_experiments/g1_gptlong_top8_32b",
|
||||
"cluster_name": "jupiter",
|
||||
"num_nodes": 24,
|
||||
"gpus_per_node": 4,
|
||||
"cpus_per_node": 288,
|
||||
"launcher": "accelerate",
|
||||
"accelerate_config_path": null,
|
||||
"deepspeed_config": "sft/lf_configs/deepspeed/ds_z3_accelerate.json",
|
||||
"master_port": 12802,
|
||||
"needs_ssh_tunnel": true,
|
||||
"needs_cuda_detection": false
|
||||
}
|
||||
Reference in New Issue
Block a user