axolotl version: 0.4.0

# base_model: Qwen/Qwen-7B
base_model: Qwen/Qwen1.5-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  # - path: mhenrichsen/alpaca_2k_test
  - path: /home/yujia/home/CN_Hateful/train_toxiCN_cn.json
  # - path: /home/yujia/home/CN_Hateful/train_toxiCN.json
  # - path: /home/yujia/home/CN_Hateful/train.json
  # - path: /home/yujia/home/CN_Hateful/train_cn.json
    ds_type: json
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/CN/toxi/5e-4/
# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/toxi/1e-5/
# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/cold/3e-4/
# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/CN/cold/3e-4/

sequence_len: 256  # supports up to 8192
sample_packing: false
pad_to_sequence_len:

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0005

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

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

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 20
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens: