base_model: NobodyExistsOnTheInternet/3epoch-miqu-limarp
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: NobodyExistsOnTheInternet/Fixed-FilteredTruthyDPO
    split: train
    type: chatml.intel
    
  - path: NobodyExistsOnTheInternet/ToxicDPOqa
    split: train
    type: chatml.intel

  - path: NobodyExistsOnTheInternet/Fixed-Distilabel-intel-orca-dpo-pairs
    split: train
    type: chatml.intel

  - path: NobodyExistsOnTheInternet/Fixed-gutenberg-dpo-v0.1
    split: train
    type: chatml.intel

    
chat_template: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./miqu-lora
save_safetensors: true
save_steps: 300


rl: dpo
chat_template: chatml


adapter: qlora
lora_model_dir:

sequence_len: 768


lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: miqu-lora
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 3
optimizer: paged_lion_8bit
lr_scheduler: cosine
learning_rate: 0.0000014

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

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

warmup_steps: 10
eval_table_size:
weight_decay: 0
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  unk_token: "</s>"


tokens:
    - "<|im_start|>"
    - "<|im_end|>"

neftune_noise_alpha: 5

hub_model_id: NobodyExistsOnTheInternet/miqu-limarp-70b-dpo
hub_strategy: all_checkpoints
hf_use_auth_token: true
push_to_hub: true
rl_adapter_ref_model: false

miqu-limarp-70b-dpo

This model was trained from scratch on the None 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: 1.4e-06
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 16
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 3960

Training results

Framework versions

PEFT 0.8.2.dev0
Transformers 4.37.0
Pytorch 2.0.1+cu117
Datasets 2.16.1
Tokenizers 0.15.0

NobodyExistsOnTheInternet/miqu-limarp-70b-dpo-safefile

miqu-limarp-70b-dpo

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NobodyExistsOnTheInternet/
miqu-limarp-70b-dpo-safefile