include axolotl config

configs/axolotl.yml

@@ -0,0 +1,65 @@
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+rl: true
+datasets:
+  - path: winglian/no_robots_rlhf
+    split: train
+test_datasets:
+  - path: winglian/no_robots_rlhf
+    split: test
+dataset_prepared_path:
+val_set_size: 0.0
+output_dir: ./qlora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: false
+pad_to_sequence_len: true
+
+lora_r: 64
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project: oh-ipo
+wandb_entity: oaaic
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 3
+optimizer: rmsprop
+lr_scheduler: cosine
+learning_rate: 5e-7
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_steps: 10
+eval_steps: 0.0
+eval_table_size:
+save_steps:
+deepspeed: deepspeed/zero3.json
+weight_decay: 0.0
+