base_model: llama3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: llama-3-8b-self-align-data-generation-results/sanitized.jsonl
    ds_type: json
    type:
      system_prompt: "You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions."
      field_system: system
      field_instruction: instruction
      field_output: response
      format: "### Instruction:\n{instruction}\n\n### Response:\n"
      no_input_format: "### Instruction:\n{instruction}\n\n### Response:\n"
dataset_prepared_path:
val_set_size: 0.05

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter: qlora
save_safetensors: true
lora_model_dir:
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

log_with: None
wandb_project: llama-3-8b-self-align-axolotl
wandb_entity:
wandb_watch:
wandb_name: qlora-prince-hps-promptfix

output_dir: qlora_decrease_lr_promptfix
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 2
num_epochs: 4
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 2e-5

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

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

warmup_steps: 100
evals_per_epoch: 8
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: false
  fsdp_offload_params: false
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: false
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
special_tokens:
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"
lora_modules_to_save:
  - embed_tokens
  - lm_head