winglian / codeforces-cot-distill-7b-v0

axolotl version: 0.10.0.dev0

base_model: Qwen/Qwen2.5-Coder-7B-Instruct

plugins:
  - axolotl.integrations.kd.KDPlugin
  - axolotl.integrations.liger.LigerPlugin

liger_rms_norm: true
liger_glu_activation: true

  # torch_compile: true

strict: false

chat_template_jinja: "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>' }}\n{%- endif %}\n"

kd_trainer: true
kd_ce_alpha: 0.2
kd_alpha: 0.8
kd_temperature: 1.1

dataloader_prefetch_factor: 256
dataloader_num_workers: 4
dataloader_pin_memory: true

gc_steps: -1  # gc at the end of each epoch

datasets:
- field_messages: messages
  message_field_content: content
  message_field_role: role
  logprobs_field: target_logprobs
  path: winglian/codeforces-cot-16k-context-topk64-prepared
  type: axolotl.integrations.kd.chat_template
  split: train
  temperature: 1.0

dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out-kd-7b
skip_prepare_dataset: false

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

wandb_project: kd-7b-codeforces
wandb_entity: axolotl-ai
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 4
num_epochs: 4
optimizer: adamw_torch_fused
lr_scheduler: rex
learning_rate: 4e-5
save_safetensors: true

train_on_inputs: false
group_by_length: false
bf16: true
fp16:
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 120
evals_per_epoch: 
eval_table_size:
saves_per_epoch: 1
debug:
weight_decay: 0.0
special_tokens:
  pad_token: <|endoftext|>
deepspeed: deepspeed_configs/zero2.json