59 lines
938 B
YAML
59 lines
938 B
YAML
base_model: bigcode/starcoder2-3b
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
|
|
datasets:
|
|
- path: mhenrichsen/alpaca_2k_test
|
|
type: alpaca
|
|
|
|
|
|
dataset_prepared_path:
|
|
val_set_size: 0.2
|
|
output_dir: ./outputs/qlora
|
|
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 8192
|
|
sample_packing: true
|
|
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_run_id:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 8
|
|
micro_batch_size: 2
|
|
num_epochs: 3
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 2e-5
|
|
|
|
bf16: auto
|
|
fp16: false
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
attn_implementation: flash_attention_2
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 4
|
|
eval_steps:
|
|
saves_per_epoch: 4
|
|
save_steps:
|
|
save_total_limit: 2
|
|
weight_decay:
|
|
special_tokens:
|