qwerrwe / configs /llama_7B_4bit.yml
winglian's picture
swap batch size for gradient accumulation steps to decouple from num gpu
c2a0792
raw
history blame
981 Bytes
base_model: decapoda-research/llama-7b-hf-int4
base_model_config: decapoda-research/llama-7b-hf
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: true
datasets:
- path: tatsu-lab/alpaca # original alpaca dataset
type: alpaca
dataset_prepared_path: data/last_run_prepared
val_set_size: 0.04
adapter: lora
lora_model_dir:
sequence_len: 2048
max_packed_sequence_len: 1024
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- v_proj
# - k_proj
# - o_proj
lora_fan_in_fan_out: false
wandb_project:
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./lora-test
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 3
warmup_steps: 100
learning_rate: 0.00003
train_on_inputs: false
group_by_length: false
bf16: true
tf32: true
gradient_checkpointing: false
early_stopping_patience: 3
resume_from_checkpoint:
auto_resume_from_checkpoints: true
local_rank:
load_4bit: true
xformers_attention: true
flash_attention: