58 lines
1.1 KiB
YAML
58 lines
1.1 KiB
YAML
base_model: EleutherAI/gpt-j-6b
|
|
base_model_config: EleutherAI/gpt-j-6b
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
strict: false
|
|
push_dataset_to_hub:
|
|
datasets:
|
|
- path: teknium/GPT4-LLM-Cleaned
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.01
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
sequence_len: 2048
|
|
max_packed_sequence_len:
|
|
lora_r: 8
|
|
lora_alpha: 32
|
|
lora_dropout: 0.05
|
|
lora_target_modules:
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
wandb_project:
|
|
wandb_watch:
|
|
wandb_run_id:
|
|
wandb_log_model:
|
|
output_dir: ./qlora-out
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 2
|
|
num_epochs: 2
|
|
optimizer: paged_adamw_8bit
|
|
torchdistx_path:
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0001
|
|
train_on_inputs: false
|
|
group_by_length: true
|
|
bf16: true
|
|
fp16: false
|
|
tf32: true
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention: true
|
|
flash_attention:
|
|
gptq_groupsize:
|
|
gptq_model_v1:
|
|
warmup_steps: 10
|
|
eval_steps: 20
|
|
save_steps:
|
|
debug:
|
|
deepspeed:
|
|
weight_decay: 0.1
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
pad_token: "<|endoftext|>"
|