22810c97b7
* use warmup_ratio as a better default than warmup steps since it's data dependent * replace remainder of warmup_steps
49 lines
907 B
YAML
49 lines
907 B
YAML
base_model: replit/replit-code-v1-3b
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
trust_remote_code: true
|
|
load_in_8bit: false
|
|
datasets:
|
|
- path: vicgalle/alpaca-gpt4
|
|
type: alpaca
|
|
dataset_prepared_path:
|
|
val_set_size: 0.05
|
|
adapter: lora
|
|
lora_model_dir:
|
|
sequence_len: 2048
|
|
max_packed_sequence_len:
|
|
lora_r: 8
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_modules:
|
|
- Wqkv
|
|
- mlp_up
|
|
- mlp_down
|
|
wandb_project: lora-replit
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
output_dir: ./outputs/lora-replit
|
|
batch_size: 8
|
|
micro_batch_size: 1
|
|
num_epochs: 4
|
|
optimizer:
|
|
torchdistx_path:
|
|
lr_scheduler:
|
|
learning_rate: 0.00001
|
|
bf16: auto
|
|
tf32: true
|
|
gradient_checkpointing:
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention:
|
|
gptq_groupsize:
|
|
gptq_model_v1:
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
weight_decay: 0
|
|
#special_tokens:
|