minionai/llama3-70b-wh_cove_thght_062024_halluc_rem_refusal_runpod_rename

adapter: lora
base_model: meta-llama/Meta-Llama-3-70B
bf16: true
dataset_prepared_path: last_run_prepared
debug: null
deepspeed: null
early_stopping_patience: null
eval_table_size: null
evals_per_epoch: 0
flash_attention: true
fp16: null
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
gradient_accumulation_steps: 1
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
group_by_length: false
hub_model_id: minionai/llama3-70b-wh_cove_thght_062024_halluc_rem_refusal_runpod
hub_strategy: all_checkpoints
learning_rate: 1e-4
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lora_target_modules: null
lr_scheduler: cosine
micro_batch_size: 1
model_type: LlamaForCausalLM
num_epochs: 3
optimizer: adamw_torch
output_dir: ./lora-out
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
wandb_entity: minionai
wandb_name: wh_cove_thght_062024_ift
wandb_project: llama3-70b
saves_per_epoch: 1
sequence_len: 8192
special_tokens:
  pad_token: <|end_of_text|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
val_set_size: 0
warmup_steps: 250
weight_decay: 0.0
datasets:
- path: minionai/wh_w_cv_thoughts_062024_halluc_filt_refusal_add_ift
  type: 
      system_prompt: ""
      system_format: "{system}"
      field_system: system
      field_instruction: instruction
      field_input: input
      field_output: output
      format: |-
        User: {instruction} {input}
        Assistant:
      # 'no_input_format' cannot include {input}
      no_input_format: "### System:\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:\nverify(\""