voidful/Qwen3.5-27B-earica-hardness

See axolotl config

axolotl version: 0.16.0.dev0

base_model: Qwen/Qwen3.5-27B
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_w_min: 0.05

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

dataset_prepared_path: ./prepared_data/rcca_tr_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/rcca-tr-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

Qwen3.5-27B-earica

This model is a fine-tuned version of Qwen/Qwen3.5-27B on the voidful/earica_text_train_v2 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: 240
• gradient_accumulation_steps: 2
• total_train_batch_size: 480
• total_eval_batch_size: 240
• 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: 384

Training results

Framework versions

• Transformers 5.3.0
• Pytorch 2.8.0+cu128
• Datasets 4.5.0
• Tokenizers 0.22.2