782b6a4216
* set fp16 to false if bf16, update bf16: auto in example YAMLs * unset fp16 so that it fallsback properly if bf16 isn't available * Update README.md [skip-ci] Co-authored-by: NanoCode012 <kevinvong@rocketmail.com> * test that bf16 disables fp16 --------- Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
38 lines
753 B
YAML
38 lines
753 B
YAML
base_model: EleutherAI/pythia-1.4b-deduped
|
|
load_in_8bit: true
|
|
datasets:
|
|
- path: teknium/GPT4-LLM-Cleaned
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0.05
|
|
adapter: lora
|
|
lora_model_dir:
|
|
sequence_len: 512
|
|
lora_r: 16
|
|
lora_alpha: 32
|
|
lora_dropout: 0.05
|
|
lora_target_modules:
|
|
- query_key_value
|
|
lora_target_linear:
|
|
lora_fan_in_fan_out: true # pythia/GPTNeoX lora specific
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
output_dir: ./lora-alpaca-pythia
|
|
gradient_accumulation_steps: 1
|
|
micro_batch_size: 4
|
|
num_epochs: 4
|
|
learning_rate: 0.00001
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: auto
|
|
tf32: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
weight_decay: 0.1
|
|
evals_per_epoch: 4
|
|
logging_steps: 1
|