base_model: tiiuae/falcon-7b
base_model_config: tiiuae/falcon-7b
trust_remote_code: true
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
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: last_run_prepared
val_set_size: 0.01
adapter: qlora
lora_model_dir:
sequence_len: 2048
max_packed_sequence_len: 2048
lora_r: 64
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: falcon-qlora
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./qlora-out
batch_size: 8
micro_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_32bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
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: false
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 10
eval_steps: 5
save_steps: 10
debug:
deepspeed:
weight_decay: 0.000001
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>"
  bos_token: ">>ABSTRACT<<"
  eos_token: "<|endoftext|>"