base_model: Aratako/Llama-Gemma-2-27b-SFT-trial1
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: Aratako/fft-simpo-4-gemma
hub_strategy: "end"
push_dataset_to_hub:
hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_cross_entropy: false
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: tokenizer_default
rl: simpo
rl_beta: 10.0
cpo_alpha: 0.05
simpo_gamma: 5.0
max_prompt_length: 512
max_length: 2048


datasets:
  - path: Aratako/HelpSteer2-Preferences-formatted
    type: gemma.custom
    train_on_split: train
  - path: Aratako/magpie-sft-v1.0-dpo-judged
    type: gemma.custom
    train_on_split: train
  - path: Aratako/aya-ja-evol-instruct-calm3-dpo-masked-formatted
    type: gemma.custom
    train_on_split: train


shuffle_merged_datasets: true
dataset_prepared_path: /workspace/data/fft-simpo-data-gemma-4
output_dir: /workspace/data/27b-fft-simpo-out-4

sequence_len: 2048
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project: 27b-fft
wandb_entity: aratako-lm
wandb_watch:
wandb_name: simpo-attempt-04
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
cosine_min_lr_ratio: 0.1
learning_rate: 3e-7

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

save_strategy: steps
save_steps: 100
save_total_limit: 1

warmup_steps: 20
eval_steps:
eval_batch_size:
eval_table_size:
eval_max_new_tokens:
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
  pad_token: <pad>

Aratako/Llama-Gemma-2-27b-CPO_SimPO-iter1

Llama-Gemma-2-27b-CPO_SimPO-iter1

概要

使用データセット

ライセンス

学習に関する詳細

Aratako/
Llama-Gemma-2-27b-CPO_SimPO-iter1