mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
56ce2e79a7
* v0 * 2 gpu setup * improve parsing from yaml * update yaml dataset example * remove restriction on flash attn * more comments * first version of the readme * pin torch * simplify requirements * just flash attn * use set env instead * simpler set env * readme * add wandb project to setup * update template * update model id * post init to capture the config and weight * extract metadata * update config * update dataset config * move env for wandb project * pre-commit * remove qwen-math from training * more instructions * unused import * remove trl old * warmup ratio * warmup ratio * change model id * change model_id * add info about CUDA_VISIBLE_DEVICES
22 lines
494 B
YAML
22 lines
494 B
YAML
compute_environment: LOCAL_MACHINE
|
|
debug: false
|
|
deepspeed_config:
|
|
deepspeed_multinode_launcher: standard
|
|
offload_optimizer_device: none
|
|
offload_param_device: none
|
|
zero3_init_flag: false
|
|
zero_stage: 2
|
|
gradient_clipping: auto
|
|
distributed_type: DEEPSPEED
|
|
downcast_bf16: 'no'
|
|
machine_rank: 0
|
|
main_training_function: main
|
|
mixed_precision: bf16
|
|
num_machines: 1
|
|
num_processes: 2
|
|
rdzv_backend: static
|
|
same_network: true
|
|
tpu_env: []
|
|
tpu_use_cluster: false
|
|
tpu_use_sudo: false
|
|
use_cpu: false
|