Qwen3.5-27B-gemini-3.1-opus-4.6-reasoning

base_model: voidful/Qwen3.5-27B-earica
low_cpu_mem_usage: true

plugins:
  - axolotl.integrations.rcca_tr.RCCATRPlugin
  - axolotl.integrations.liger.LigerPlugin

liger_rms_norm: true
liger_glu_activation: true

rcca_tr_trainer: true
rcca_tr_tau_p: 2.0
rcca_tr_T_p: 1.0
rcca_tr_tau_delta: 0.8
rcca_tr_T_delta: 1.0
rcca_tr_w_min: 0.05
rcca_tr_prior_cache_path: ./prior_cache/prior_cache_27b_dt.pt

datasets:
  - path: voidful/gemini-3.1-opus-4.6-reasoning-merged_v2
    type: chat_template
    split: train

dataset_prepared_path: ./prepared_data/rcca_tr_27b


chat_template: qwen3_5

sequence_len: 8192
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/rcca-tr-27b-dt

deepspeed: deepspeed_configs/zero2.json

hub_model_id: voidful/Qwen3.5-27B-gemini-3.1-opus-4.6-reasoning
push_to_hub: true
hub_strategy: end

log_on_each_node: false
logging_steps: 1