初始化项目,由ModelHub XC社区提供模型

Model: cs-552-2026-flab/multilingual_model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-13 10:03:22 +08:00
commit aed8c2363a
12 changed files with 836 additions and 0 deletions

107
hydra/.hydra/config.yaml Normal file
View File

@@ -0,0 +1,107 @@
model:
hf_id: Qwen/Qwen3-1.7B
local_path: /shared-ro/models/Qwen3-1.7B
dtype: bfloat16
attn_impl: flash_attention_2
max_model_len: 4096
data:
name: nemotron_math
loader: load_nemotron_math
kwargs:
limit: 50000
split: train
max_total_tokens: 3800
seed: 0
training:
recipe: sft
epochs: 1
per_device_train_batch_size: 1
gradient_accumulation_steps: 16
learning_rate: 5.0e-06
warmup_ratio: 0.03
lr_scheduler_type: cosine
gradient_checkpointing: true
bf16: true
max_seq_length: 4096
max_steps: -1
max_grad_norm: 1.0
optim: adamw_torch
assistant_only_loss: true
logging_steps: 10
save_steps: 500
save_total_limit: 2
report_to: wandb
qlora: false
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
deepspeed: configs/deepspeed_zero2.json
adapter_model_dir: null
domain:
name: multilingual
thinking_mode: false
benchmark: multilingual
languages:
- it
- es
- zh
- ru
- hi
target_format: boxed
max_options: 20
reward_fn: multilingual
system_instruction: Choose the best option. Do not write an explanation. Return
exactly one final answer in the form \boxed{LETTER}.
template_boxed_instruction: Choose the best option. Do not write an explanation.
Return exactly one final answer in the form \boxed{LETTER}.
post_train:
enabled: false
merge_adapter: false
merged_output_dir: null
domain_override: null
evals: []
seed: 42
run_id: ${now:%Y%m%d_%H%M%S}
output_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged
wandb:
project: flab-cs552
entity: cs-552-2026-flab
mode: null
tags: []
notes: null
eval:
model_dir: null
rows_source: samples
method: null
system_prompt: null
use_domain_system_prompt: false
force_domain_template: false
'n': 8
temperature: 0.7
top_p: 0.95
max_model_len: 4096
max_tokens: 4096
samples_dir: null
push:
model_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
base_model_dir: null
es:
base_model_dir: null
data: null
hf_push:
enabled: false
org: cs-552-2026-flab
repo: null
private: false
vllm_validate: true
commit_message: null
validate_after_train: false
vllm_validate: true

162
hydra/.hydra/hydra.yaml Normal file
View File

@@ -0,0 +1,162 @@
hydra:
run:
dir: ${output_dir}/hydra
sweep:
dir: ${output_dir}/hydra_sweep
subdir: ${hydra.job.num}
launcher:
_target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
sweeper:
_target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
max_batch_size: null
params: null
help:
app_name: ${hydra.job.name}
header: '${hydra.help.app_name} is powered by Hydra.
'
footer: 'Powered by Hydra (https://hydra.cc)
Use --hydra-help to view Hydra specific help
'
template: '${hydra.help.header}
== Configuration groups ==
Compose your configuration from those groups (group=option)
$APP_CONFIG_GROUPS
== Config ==
Override anything in the config (foo.bar=value)
$CONFIG
${hydra.help.footer}
'
hydra_help:
template: 'Hydra (${hydra.runtime.version})
See https://hydra.cc for more info.
== Flags ==
$FLAGS_HELP
== Configuration groups ==
Compose your configuration from those groups (For example, append hydra/job_logging=disabled
to command line)
$HYDRA_CONFIG_GROUPS
Use ''--cfg hydra'' to Show the Hydra config.
'
hydra_help: ???
hydra_logging:
version: 1
formatters:
simple:
format: '[%(asctime)s][HYDRA] %(message)s'
handlers:
console:
class: logging.StreamHandler
formatter: simple
stream: ext://sys.stdout
root:
level: INFO
handlers:
- console
loggers:
logging_example:
level: DEBUG
disable_existing_loggers: false
job_logging:
version: 1
formatters:
simple:
format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
handlers:
console:
class: logging.StreamHandler
formatter: simple
stream: ext://sys.stdout
file:
class: logging.FileHandler
formatter: simple
filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
root:
level: INFO
handlers:
- console
- file
disable_existing_loggers: false
env: {}
mode: RUN
searchpath: []
callbacks: {}
output_subdir: .hydra
overrides:
hydra:
- hydra.mode=RUN
task:
- domain=multilingual_nothink_direct
- push.model_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
- output_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged
job:
name: merge_peft
chdir: false
override_dirname: domain=multilingual_nothink_direct,output_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged,push.model_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
id: ???
num: ???
config_name: base
env_set: {}
env_copy: []
config:
override_dirname:
kv_sep: '='
item_sep: ','
exclude_keys: []
runtime:
version: 1.3.2
version_base: '1.3'
cwd: /scratch/runs/cs552-mazniche-g07-a42-qwen-success-r64-095002
config_sources:
- path: hydra.conf
schema: pkg
provider: hydra
- path: /scratch/runs/cs552-mazniche-g07-a42-qwen-success-r64-095002/configs
schema: file
provider: main
- path: ''
schema: structured
provider: schema
output_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged/hydra
choices:
post_train: disabled
domain: multilingual_nothink_direct
training: sft
data: nemotron_math
model: qwen3_17b
hydra/env: default
hydra/callbacks: null
hydra/job_logging: default
hydra/hydra_logging: default
hydra/hydra_help: default
hydra/help: default
hydra/sweeper: basic
hydra/launcher: basic
hydra/output: default
verbose: false

View File

@@ -0,0 +1,3 @@
- domain=multilingual_nothink_direct
- push.model_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
- output_dir=/scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged