jermyn/CodeQwen1.5-7B-Chat-lora8-NLQ2Cypher

# base_model: deepseek-ai/deepseek-coder-1.3b-instruct
base_model: Qwen/CodeQwen1.5-7B-Chat
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_mistral_derived_model: false

load_in_8bit: true
load_in_4bit: false
strict: false

lora_fan_in_fan_out: false
data_seed: 49
seed: 49

datasets:
  - path: sample_data/alpaca_synth_cypher.jsonl
    type: sharegpt
    conversation: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-alpaca-codeqwen1.5-7b-chat-lora8
# output_dir: ./qlora-alpaca-out

hub_model_id: jermyn/CodeQwen1.5-7B-Chat-lora8-NLQ2Cypher
# hub_model_id: jermyn/deepseek-code-1.3b-inst-NLQ2Cypher

adapter: lora   # 'qlora' or leave blank for full finetune
lora_model_dir:

sequence_len: 896
sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
# lora_target_modules:
#   - gate_proj
#   - down_proj
#   - up_proj
#   - q_proj
#   - v_proj
#   - k_proj
#   - o_proj

# If you added new tokens to the tokenizer, you may need to save some LoRA modules because they need to know the new tokens.
# For LLaMA and Mistral, you need to save `embed_tokens` and `lm_head`. It may vary for other models.
# `embed_tokens` converts tokens to embeddings, and `lm_head` converts embeddings to token probabilities.
# https://github.com/huggingface/peft/issues/334#issuecomment-1561727994
# lora_modules_to_save:
#   - embed_tokens
#   - lm_head

wandb_project: fine-tune-axolotl
wandb_entity: jermyn

gradient_accumulation_steps: 2
micro_batch_size: 8
eval_batch_size: 8
num_epochs: 6
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0005
max_grad_norm: 1.0
adam_beta2: 0.95
adam_epsilon: 0.00001

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

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

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
# saves_per_epoch: 6
save_steps: 10
save_total_limit: 3
debug:
weight_decay: 0.0
fsdp:
fsdp_config:
# special_tokens:
#   bos_token: "<s>"
#   eos_token: "</s>"
#   unk_token: "<unk>"
save_safetensors: true