Upload miqumaid2x70bDPO.yaml

miqumaid2x70bDPO.yaml

@@ -0,0 +1,77 @@
+base_model: NeverSleep/MiquMaid-v2-70B
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+is_llama_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+rl: dpo
+datasets:
+  - path: NobodyExistsOnTheInternet/ToxicDPOqa
+    split: train
+    type: chatml.alpaca
+  - path: Undi95/toxic-dpo-v0.1-NoWarning
+    split: train
+    type: chatml.alpaca2
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 1024
+sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 16
+lora_alpha: 8
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project: MiquMaidDPO
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 3
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.000001
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+eval_steps:
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed: ./axolotl/deepspeed_configs/zero2.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"