qwerrwe / configs /cerebras_1_3B_alpaca.yml
winglian's picture
swap batch size for gradient accumulation steps to decouple from num gpu
c2a0792
raw
history blame
939 Bytes
base_model: cerebras/Cerebras-GPT-1.3B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: true
datasets:
- path: data/alpaca_data_gpt4.jsonl
type: alpaca
- path: data/vicuna_cleaned.jsonl
type: sharegpt
- path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
type: gpteacher
- path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
type: gpteacher
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
adapter: lora
sequence_len: 2048
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- c_attn
lora_fan_in_fan_out: false
wandb_project: pythia-1.4b-lora
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./lora-alpaca
gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 5
learning_rate: 0.0003
train_on_inputs: false
group_by_length: false
bf16: True
tf32: True
gradient_checkpointing:
early_stopping_patience:
resume_from_checkpoint:
local_rank: