move unmaintained examples to archive (#2903) [skip ci]
This commit is contained in:
48
examples/archived/gptj/qlora.yml
Normal file
48
examples/archived/gptj/qlora.yml
Normal file
@@ -0,0 +1,48 @@
|
||||
base_model: EleutherAI/gpt-j-6b
|
||||
# Automatically upload checkpoint and final model to HF
|
||||
# hub_model_id: username/custom_model_name
|
||||
|
||||
load_in_8bit: false
|
||||
load_in_4bit: true
|
||||
push_dataset_to_hub:
|
||||
datasets:
|
||||
- path: teknium/GPT4-LLM-Cleaned
|
||||
type: alpaca
|
||||
dataset_prepared_path:
|
||||
val_set_size: 0.05
|
||||
adapter: qlora
|
||||
lora_model_dir:
|
||||
sequence_len: 2048
|
||||
max_packed_sequence_len:
|
||||
lora_r: 8
|
||||
lora_alpha: 32
|
||||
lora_dropout: 0.05
|
||||
lora_target_linear: true
|
||||
wandb_project:
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name:
|
||||
wandb_log_model:
|
||||
output_dir: ./outputs/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
|
||||
bf16: auto
|
||||
tf32: true
|
||||
gradient_checkpointing: true
|
||||
resume_from_checkpoint:
|
||||
logging_steps: 1
|
||||
xformers_attention: true
|
||||
flash_attention:
|
||||
gptq_groupsize:
|
||||
gptq_model_v1:
|
||||
warmup_steps: 10
|
||||
evals_per_epoch: 4
|
||||
saves_per_epoch: 1
|
||||
weight_decay: 0.1
|
||||
special_tokens:
|
||||
pad_token: "<|endoftext|>"
|
||||
Reference in New Issue
Block a user