9f824ef76a
* simplify the example configs to be more minimal and less daunting * drop empty s2_attention from example yamls
46 lines
862 B
YAML
46 lines
862 B
YAML
base_model: NousResearch/Meta-Llama-3.1-8B
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: tatsu-lab/alpaca
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.05
|
|
output_dir: ./outputs/out
|
|
|
|
sequence_len: 8192
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 8
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
optimizer: paged_adamw_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 2e-5
|
|
|
|
bf16: auto
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: false
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_steps: 100
|
|
evals_per_epoch: 2
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
special_tokens:
|
|
pad_token: <|end_of_text|>
|