Qwen3.5-9B-gemini-3.1-opus-4.6-reasoning

# Example config for RCCA-TR A+ (Reliability-Calibrated Conflict-Aware Trust-Region) fine-tuning
# A+ variant: only 1 model in GPU memory (active model)
# Prior = offline cache, EMA = drift buffer

base_model: Qwen/Qwen3.5-9B

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

liger_rms_norm: true
liger_glu_activation: true

# Enable RCCA-TR trainer
rcca_tr_trainer: true

# Conflict score hyperparameters
rcca_tr_conflict_lambda1: 1.0      # weight for surprisal in conflict score
rcca_tr_conflict_lambda2: 0.5      # weight for margin-based conflict
rcca_tr_conflict_tau: 1.0          # temperature for conflict sigmoid

# Reliability score hyperparameters
rcca_tr_reliability_beta: 0.5      # balance between stability and evidence
rcca_tr_reliability_tau: 1.0       # temperature for reliability sigmoid

# Trust-region hyperparameters
rcca_tr_epsilon_min: 0.01          # minimum trust-region radius
rcca_tr_epsilon_max: 1.0           # maximum trust-region radius
rcca_tr_kl_lambda: 1.0             # Lagrange multiplier for KL penalty
rcca_tr_use_smooth_objective: true  # smooth g(r_t)*KL vs hinge

# Drift buffer (replaces EMA model)
rcca_tr_ema_decay: 0.999           # decay rate for drift buffer
rcca_tr_drift_gamma: 1.0           # drift → reliability scaling

# Prior cache (optional; omit to use fallback mode)
# rcca_tr_prior_cache_path: ./prior_cache/prior_cache.pt

# Dataset
datasets:
  - path: voidful/gemini-3.1-opus-4.6-reasoning-merged
    type: chat_template
    split: train

dataset_prepared_path: ./prepared_data/rcca_tr

chat_template: qwen3_5

# Training settings
sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 1
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: 0

deepspeed: deepspeed_configs/zero2.json

val_set_size: 0.05

save_strategy: epoch

output_dir: ./outputs/rcca-tr-fft

hub_model_id: voidful/Qwen3.5-9B-gemini-3.1-opus-4.6-reasoning
push_to_hub: true
hub_strategy: end

log_on_each_node: false
logging_steps: 1