File size: 967 Bytes
ce24f5e 8d959a7 ce24f5e 8d959a7 ce24f5e 8d959a7 ce24f5e 8d959a7 ce24f5e 77fca25 ce24f5e 949a27b ce24f5e 8d959a7 ce24f5e 8d959a7 949a27b 8d959a7 ce24f5e 05fffb5 abddcf4 ce24f5e 949a27b 8d959a7 ce24f5e 949a27b ce24f5e 8d959a7 ce24f5e 8d959a7 d1aed4c ce24f5e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
base_model: EleutherAI/pythia-1.4b-deduped
model_type: GPTNeoXForCausalLM
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
lora_model_dir:
sequence_len: 2048
lora_r: 8
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
- query_key_value
# - xxx
lora_fan_in_fan_out: true # pythia/GPTNeoX lora specific
wandb_project: pythia-1.4b-lora
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./lora-alpaca
batch_size: 48
micro_batch_size: 4
num_epochs: 5
learning_rate: 0.00001
train_on_inputs: false
group_by_length: false
bf16: True
tf32: True
early_stopping_patience:
resume_from_checkpoint:
local_rank:
|