github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-07-02 02:02:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

update style

Browse Source
This commit is contained in:
Tong Li 2025-03-31 11:44:10 +08:00
parent 729456957a
commit 27d0108c9f
1 changed files with 20 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
applications/ColossalChat/rl_example.py
View File

@ -11,10 +11,26 @@ if __name__ == "__main__":
parser.add_argument("-t", "--num-trainers", type=int, default=2)
parser.add_argument("-i", "--num-inferencer", type=int, default=2)
parser.add_argument("-g", "--num-generations", type=int, default=8, help="Number of generations per prompt.")
parser.add_argument("-ibs", "--inference-batch-size", type=int, default=64, help="Number of prompts to generate per step.")
parser.add_argument("-imbs", "--inference-microbatch-size", type=int, default=8, help="Number of prompts to send from the producer to the consumer.")
parser.add_argument("-tbs", "--train-batch-size", type=int, default=32, help="Number of prompts to update policy model.")
parser.add_argument("-tMbs", "--train-minibatch-size", type=int, default=1, help="Number of prompts per device. Number of samples = tMbs * num of generation per prompt.")
parser.add_argument(
"-ibs", "--inference-batch-size", type=int, default=64, help="Number of prompts to generate per step."
)
parser.add_argument(
"-imbs",
"--inference-microbatch-size",
type=int,
default=8,
help="Number of prompts to send from the producer to the consumer.",
)
parser.add_argument(
"-tbs", "--train-batch-size", type=int, default=32, help="Number of prompts to update policy model."
)
parser.add_argument(
"-tMbs",
"--train-minibatch-size",
type=int,
default=1,
help="Number of prompts per device. Number of samples = tMbs * num of generation per prompt.",
)
parser.add_argument("-tmbs", "--train-microbatch-size", type=int, default=2, help="Number of samples per device.")
parser.add_argument("-b", "--backend", type=str, default="transformers", choices=["transformers, vllm"])
parser.add_argument("-a", "--algo", type=str, default="GRPO", choices=["Simple", "GRPO", "EvalGRPO"])