NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-26 17:13:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

math zero ymls

Browse source
This commit is contained in:
Jai Suphavadeeprasit 2026-02-04 17:52:16 -05:00
parent 93da3874e7
commit 4309793e4a
2 changed files with 42 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

21
example_trainer/configs/math_zero_lora.yaml Normal file
View file

@ -0,0 +1,21 @@
env:
tokenizer_name: "Qwen/Qwen3-4B-Instruct-2507"
rollout_server_url: "http://localhost:8002"
max_token_length: 8192
start_tok_length: 8192
group_size: 8
batch_size: 64
total_steps: 120
steps_per_eval: 20
use_wandb: true
wandb_name: "math-zero-lora-env"
eval_limit_ratio: 0.1
max_num_workers_per_node: 24
openai:
base_url: "http://localhost:9002/v1"
model_name: "Qwen/Qwen3-4B-Instruct-2507"
server_type: "vllm"
api_key: "x"
num_requests_for_eval: 256
weight: 1.0

21
example_trainer/configs/math_zero_shared.yaml Normal file
View file

@ -0,0 +1,21 @@
env:
tokenizer_name: "Qwen/Qwen3-4B-Instruct-2507"
rollout_server_url: "http://localhost:8001"
max_token_length: 8192
start_tok_length: 8192
group_size: 8
batch_size: 64
total_steps: 120
steps_per_eval: 20
use_wandb: true
wandb_name: "math-zero-shared-env"
eval_limit_ratio: 0.1
max_num_workers_per_node: 24
openai:
base_url: "http://localhost:9001/v1"
model_name: "Qwen/Qwen3-4B-Instruct-2507"
server_type: "vllm"
api_key: "x"
num_requests_for_eval: 256
weight: 1.0