Mistral Small 24B Instruct 2501 Reasoning

axolotl 版本: a98526ef7843a3e8aa006f260e6b4fb8912b5f1a

base_model: mistralai/Mistral-Small-24B-Instruct-2501

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

datasets:
  - path: yentinglin/s1K-1.1-trl-format
    type: chat_template
    chat_template: tokenizer_default
    field_messages: messages
    message_field_role: role
    message_field_content: content
  - path: open-r1/OpenR1-Math-220k
    type: chat_template
    chat_template: tokenizer_default
    field_messages: messages
    message_field_role: from
    message_field_content: value
dataset_prepared_path:
val_set_size: 0.0
output_dir: ./placeholder/

sequence_len: 32768
sample_packing: true
eval_sample_packing: False
pad_to_sequence_len: true

wandb_project: Reasoning
wandb_entity:
wandb_watch:
wandb_name: Mistral-24B-SFT-220k
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 5
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5

train_on_inputs: false
group_by_length: false
bf16: auto
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
logging_steps: 1
flash_attention: true

warmup_ratio: 0.1
saves_per_epoch: 2
weight_decay: 0.0
deepspeed: deepspeed_configs/zero3_bf16.json
special_tokens:
  pad_token: "<pad>"