base_model: gpt2-xl
model_type: GPT2LMHeadModel
tokenizer_type: GPT2Tokenizer
is_gpt2_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: train_naming.csv
    type: csv
    column_names:
      - Label
      - Text
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 1096
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: 
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

mlflow_experiment_name: colab-example

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 4
max_steps: 20
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 5e-5

train_on_inputs: false
group_by_length: false
bf16: false
fp16: true
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: false
flash_attention: true

warmup_steps: 10
evals_per_epoch:
saves_per_epoch:
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
save_safetensors: true