base_model: cerebras/Cerebras-GPT-1.3B
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:
val_set_size: 0.05
adapter: qlora
lora_model_dir:
sequence_len: 2048
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
  - c_fc
  - c_attn
  - c_proj
lora_target_linear:
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
output_dir: ./qlora-out
batch_size: 4
micro_batch_size: 4
num_epochs: 2
optimizer: paged_adamw_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
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
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>"