Qwen3.5-27B-earica

base_model: Qwen/Qwen3.5-27B
low_cpu_mem_usage: true

plugins:
  - axolotl.integrations.drift.DriftPlugin
  - axolotl.integrations.liger.LigerPlugin

liger_rms_norm: true
liger_glu_activation: true

drift_trainer: true
drift_rho: 0.999
drift_beta: 0.5
drift_tau: 1.0
drift_lambda: 1.0

datasets:
  - path: voidful/earica_text_train_v2
    type: chat_template
    field_messages: conversations
    split: train
    split_thinking: true

dataset_prepared_path: ./prepared_data/drift_27b


chat_template: qwen3_5

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: false

gradient_accumulation_steps: 2
micro_batch_size: 1
batch_flattening: false
group_by_length: true
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 2e-5

bf16: true
gradient_checkpointing: true
flash_attention: true
dataloader_num_workers: 4
val_set_size: 0.05
save_strategy: epoch
output_dir: ./outputs/drift-27b

deepspeed: deepspeed_configs/zero2.json

hub_model_id: voidful/Qwen3.5-27B-earica
push_to_hub: true
hub_strategy: end

log_on_each_node: false
logging_steps: 1