winglian's picture
swap batch size for gradient accumulation steps to decouple from num gpu
c2a0792
raw
history blame
1.26 kB
base_model: Neko-Institute-of-Science/LLaMA-7B-4bit-128g
base_model_config: Neko-Institute-of-Science/LLaMA-7B-4bit-128g
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code:
load_in_8bit: true
gptq: true
datasets:
- path: vicgalle/alpaca-gpt4
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.02
adapter:
lora_model_dir:
sequence_len: 2048
max_packed_sequence_len:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- v_proj
lora_fan_in_fan_out: false
wandb_project: llama-7b-lora-int4
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./llama-7b-lora-int4
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0000002
train_on_inputs: false
group_by_length: false
fp16: true
bf16: false
tf32: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 5
xformers_attention:
flash_attention:
gradient_checkpointing: true
gptq_groupsize: 128
gptq_model_v1: false
warmup_steps: 20
eval_steps: 110
save_steps: 660
debug:
deepspeed:
weight_decay: 0.0001
fsdp:
fsdp_config:
tokens:
pad_token: "[PAD]"
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"