axolotl-ai-co/romulus-mistral-nemo-12b-simpo

base_model: winglian/m12b-20240721-test010
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: chatml
rl: simpo
rl_beta: 2.5
cpo_alpha: 0.05
simpo_gamma: 0.1
datasets:
  - path: princeton-nlp/gemma2-ultrafeedback-armorm
    type: chat_template.default
    chat_template: chatml
    field_messages: chosen
    field_chosen: chosen
    field_rejected: rejected
    message_field_role: role
    message_field_content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant

dataset_prepared_path:
val_set_size: 0.0
output_dir: ./outputs/simpo-out

save_safetensors: true
save_only_model: true  # fsdp seems to crap out saving the optimizer

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true

adapter: 
lora_model_dir:
lora_r: 256
lora_alpha: 256
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
  # peft_use_rslora: true

wandb_project: romulus-12b
wandb_entity: oaaic
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 5.0e-7

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config: