# 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/earica_text_train
    type: chat_template
    field_messages: conversations
    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-earica
push_to_hub: true
hub_strategy: end

log_on_each_node: false
logging_steps: 1

Qwen3.5-9B-earica

This model is a fine-tuned version of Qwen/Qwen3.5-9B on the voidful/earica_text_train dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 80
gradient_accumulation_steps: 4
total_train_batch_size: 320
total_eval_batch_size: 80
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 11
training_steps: 375

Training results

Framework versions

Transformers 5.3.0
Pytorch 2.10.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2