# this is the huggingface model that contains *.pt, *.safetensors, or *.bin files
# this can also be a relative path to a model on disk
base_model: ./llama-7b-hf
# you can specify an ignore pattern if the model repo contains more than 1 model type (*.pt, etc)
base_model_ignore_patterns:
# if the base_model repo on hf hub doesn't include configuration .json files,
# you can set that here, or leave this empty to default to base_model
base_model_config: ./llama-7b-hf
# If you want to specify the type of model to load, AutoModelForCausalLM is a good choice too
model_type: AutoModelForCausalLM
# Corresponding tokenizer for the model AutoTokenizer is a good choice
tokenizer_type: AutoTokenizer
# Trust remote code for untrusted source
trust_remote_code:

# whether you are training a 4-bit GPTQ quantized model
gptq: true
gptq_groupsize: 128 # group size
gptq_model_v1: false # v1 or v2

# this will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer
load_in_8bit: true
# use bitsandbytes 4 bit
load_in_4bit:

# Use CUDA bf16
bf16: true # bool or 'full' for `bf16_full_eval`. require >=ampere
# Use CUDA fp16
fp16: true
# Use CUDA tf32
tf32: true # require >=ampere

# a list of one or more datasets to finetune the model with
datasets:
  # this can be either a hf dataset, or relative path
  - path: vicgalle/alpaca-gpt4
  # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]
    type: alpaca # format OR format:prompt_style (chat/instruct)
    data_files: # path to source data files
    shards: # number of shards to split data into

# axolotl attempts to save the dataset as an arrow after packing the data together so
# subsequent training attempts load faster, relative path
dataset_prepared_path: data/last_run_prepared
# push prepared dataset to hub
push_dataset_to_hub: # repo path
# whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
# required to be true when used in combination with `push_dataset_to_hub`
hf_use_auth_token: # boolean
# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc
val_set_size: 0.04
# Num shards for whole dataset
dataset_shard_num:
# Index of shard to use for whole dataset
dataset_shard_idx:

# the maximum length of an input to train with, this should typically be less than 2048
# as most models have a token/context limit of 2048
sequence_len: 2048
# max sequence length to concatenate training samples together up to
# inspired by StackLLaMA. see https://huggingface.co/blog/stackllama#supervised-fine-tuning
max_packed_sequence_len: 1024

# if you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model
adapter: lora
# if you already have a lora model trained that you want to load, put that here
# lora hyperparameters
lora_model_dir:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
#  - k_proj
#  - o_proj
#  - gate_proj
#  - down_proj
#  - up_proj
lora_target_linear: # if true, will target all linear layers
lora_modules_to_save:
#  - embed_tokens
#  - lm_head
lora_out_dir:
lora_fan_in_fan_out: false

# wandb configuration if you're using it
wandb_mode:
wandb_project:
wandb_watch:
wandb_run_id:
wandb_log_model: # 'checkpoint'

# where to save the finished model to
output_dir: ./completed-model

# training hyperparameters
batch_size: 8
micro_batch_size: 2
eval_batch_size: 2
num_epochs: 3
warmup_steps: 100
learning_rate: 0.00003
logging_steps:

# whether to mask out or include the human's prompt from the training labels
train_on_inputs: false
# don't use this, leads to wonky training (according to someone on the internet)
group_by_length: false

# does not work with current implementation of 4-bit LoRA
gradient_checkpointing: false

# stop training after this many evaluation losses have increased in a row
# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
early_stopping_patience: 3

# specify a scheduler and kwargs to use with the optimizer
lr_scheduler: # 'one_cycle' | 'log_sweep' | empty for cosine
lr_scheduler_kwargs:

# for one_cycle optim
lr_div_factor: # learning rate div factor

# for log_sweep optim
log_sweep_min_lr:
log_sweep_max_lr:

# specify optimizer
optimizer:
# specify weight decay
weight_decay:

# whether to use xformers attention patch https://github.com/facebookresearch/xformers:
xformers_attention:
# whether to use flash attention patch https://github.com/HazyResearch/flash-attention:
flash_attention:  # require a100 for llama

# resume from a specific checkpoint dir
resume_from_checkpoint:
# if resume_from_checkpoint isn't set and you simply want it to start where it left off
# be careful with this being turned on between different models
auto_resume_from_checkpoints: false

# don't mess with this, it's here for accelerate and torchrun
local_rank:

# add or change special tokens
special_tokens:
  # bos_token: "<s>"
  # eos_token: "</s>"
  # unk_token: "<unk>"
# add extra tokens
tokens:

# FSDP
fsdp:
fsdp_config:

# Deepspeed
deepspeed:

# Path to torch distx for optim 'adamw_anyprecision'
torchdistx_path:

# Set padding for data collator to 'longest'
collator_pad_to_longest:

# Debug mode
debug:

# Seed
seed:

# Allow overwrite yml config using from cli
strict: