File size: 1,051 Bytes
937f44f 949a27b 8d43785 949a27b 77fca25 949a27b 87e073d d060c80 949a27b 05fffb5 949a27b 8d43785 949a27b 80b2ed2 d1aed4c 949a27b |
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 43 44 45 |
base_model: huggyllama/llama-65b
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: true
datasets:
- path: data/alpaca_data_gpt4.jsonl
type: alpaca
- path: anon8231489123/ShareGPT_Vicuna_unfiltered
data_files: ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json
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: 0.04
adapter: lora
lora_model_dir:
sequence_len: 2048
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-65b-lora
wandb_watch:
wandb_run_id:
wandb_log_model: checkpoint
output_dir: ./lora-llama-alpaca
batch_size: 128
micro_batch_size: 16
warmup_steps: 1000
save_steps:
num_epochs: 5
learning_rate: 0.00003
train_on_inputs: false
group_by_length: false
bf16: true
tf32: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
|