71 lines
1.4 KiB
YAML
71 lines
1.4 KiB
YAML
# This file is copied from https://github.com/OpenAccess-AI-Collective/axolotl/blob/main/examples/llama-3/qlora.yml
|
|
base_model: meta-llama/Meta-Llama-3-8B
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: AutoTokenizer
|
|
|
|
load_in_4bit: true
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: aaditya/alpaca_subset_1
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0
|
|
output_dir: ./qlora-out
|
|
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 256
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_modules:
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
num_epochs: 4
|
|
# paged_adamw_32bit is not supported
|
|
# due to bitsandbytes issue https://github.com/TimDettmers/bitsandbytes/issues/1180
|
|
# optimizer: paged_adamw_32bit
|
|
optimizer: adamw_torch
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: true
|
|
fp16: false
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
# flash_attention is not supported
|
|
flash_attention: false
|
|
|
|
warmup_steps: 10
|
|
evals_per_epoch: 4
|
|
eval_table_size:
|
|
saves_per_epoch: 1
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.0
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
pad_token: "<|end_of_text|>"
|