arsenic-nemo-unleashed-12B

base_model: MarinaraSpaghetti/NemoMix-Unleashed-12B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

save_safetensors: true

load_in_8bit: false
load_in_4bit: true
strict: false

special_tokens:
  pad_token: <pad>

rl: dpo
# total_num_tokens: 
datasets:
  - path: jondurbin/gutenberg-dpo-v0.1
    split: train
    type:
      field_system: system
      field_prompt: prompt
      field_chosen: chosen
      field_rejected: rejected
      prompt_format: "[INST]{prompt}[/INST]"
      chosen_format: "{chosen}"
      rejected_format: "{rejected}"
  - path: unalignment/toxic-dpo-v0.2
    split: train
    type:
      field_system: system
      field_prompt: prompt
      field_chosen: chosen
      field_rejected: rejected
      prompt_format: "[INST]{prompt}[/INST]"
      chosen_format: "{chosen}"
      rejected_format: "{rejected}"

dataset_prepared_path: prepared-dpo
output_dir: ./dpoq
val_set_size: 0.001

seed: 1

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

chat_template: inst

adapter: qlora
lora_model_dir:
lora_r: 256
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_dora: true

wandb_project: unleashed-qlora-dpo
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00002
cosine_min_lr_ratio: 0.1
cosine_constant_lr_ratio: 0.95

train_on_inputs: false
group_by_length: false
bf16: true
fp16:
tf32: false

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

warmup_steps: 16
evals_per_epoch: 8
saves_per_epoch: 8
save_total_limit: 2
debug:
deepspeed:
weight_decay: 0.001
fsdp:
fsdp_config: