File size: 2,187 Bytes
ca11ae9 72bf8aa 79a8f52 72bf8aa a7a9a14 72bf8aa ca11ae9 72bf8aa e50a64e f544ab2 ca11ae9 72bf8aa fb3d40f ca11ae9 72bf8aa ca11ae9 72bf8aa ca11ae9 72bf8aa ca11ae9 a52f481 7019509 72bf8aa a1da39c 72bf8aa ca11ae9 c9c0503 fb3d40f 8b79ff0 ca11ae9 72bf8aa ca11ae9 72bf8aa 782b6a4 72bf8aa fb3d40f 72bf8aa 5f79b82 72bf8aa e799e08 72bf8aa |
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 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
# 1b: tiiuae/falcon-rw-1b
# 40b: tiiuae/falcon-40b
base_model: tiiuae/falcon-7b
# required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
trust_remote_code: true
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
# enable 4bit for QLoRA
load_in_4bit: true
gptq: false
strict: false
push_dataset_to_hub:
datasets:
- path: QingyiSi/Alpaca-CoT
data_files:
- Chain-of-Thought/formatted_cot_data/gsm8k_train.json
type: "alpaca:chat"
dataset_prepared_path:
val_set_size: 0.05
# enable QLoRA
adapter: qlora
lora_model_dir:
sequence_len: 2048
max_packed_sequence_len:
# hyperparameters from QLoRA paper Appendix B.2
# "We find hyperparameters to be largely robust across datasets"
lora_r: 64
lora_alpha: 16
# 0.1 for models up to 13B
# 0.05 for 33B and 65B models
lora_dropout: 0.05
# add LoRA modules on all linear layers of the base model
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./qlora-out
# QLoRA paper Table 9
# - 16 for 7b & 13b
# - 32 for 33b, 64 for 64b
# Max size tested on A6000
# - 7b: 40
# - 40b: 4
# decrease if OOM, increase for max VRAM utilization
micro_batch_size: 1
gradient_accumulation_steps: 2
num_epochs: 4
# Optimizer for QLoRA
optimizer: paged_adamw_32bit
torchdistx_path:
lr_scheduler: cosine
# QLoRA paper Table 9
# - 2e-4 for 7b & 13b
# - 1e-4 for 33b & 64b
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
# stop training after this many evaluation losses have increased in a row
# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
early_stopping_patience: 3
resume_from_checkpoint:
auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.000001
fsdp:
fsdp_config:
special_tokens:
pad_token: "<|endoftext|>"
bos_token: "<|endoftext|>"
eos_token: "<|endoftext|>"
|