architecture: backbone_dtype: float16 force_embedding_gradients: false gradient_checkpointing: true intermediate_dropout: 0.0 pretrained: true pretrained_weights: '' augmentation: random_parent_probability: 0.0 skip_parent_probability: 0.0 token_mask_probability: 0.0 dataset: add_eos_token_to_answer: true add_eos_token_to_prompt: true add_eos_token_to_system: true answer_column: output chatbot_author: H2O.ai chatbot_name: h2oGPT data_sample: 1.0 data_sample_choice: - Train - Validation limit_chained_samples: false mask_prompt_labels: true parent_id_column: None personalize: false prompt_column: - instruction system_column: prompt text_answer_separator: <|answer|> text_prompt_start: <|prompt|> text_system_start: <|system|> train_dataframe: /app/h2o-llmstudio/data/user/Trial_M1/M1.csv validation_dataframe: None validation_size: 0.01 validation_strategy: automatic environment: compile_model: false find_unused_parameters: false gpus: - '0' - '1' huggingface_branch: main mixed_precision: true number_of_workers: 8 seed: -1 trust_remote_code: true use_fsdp: false experiment_name: M1_llama llm_backbone: meta-llama/Llama-2-7b-hf logging: logger: None neptune_project: '' number_of_texts: 10 output_directory: /app/h2o-llmstudio/output/user/M1_llama/ prediction: batch_size_inference: 0 do_sample: false max_length_inference: 256 metric: BLEU metric_gpt_model: gpt-3.5-turbo-0301 min_length_inference: 2 num_beams: 1 num_history: 4 repetition_penalty: 1.2 stop_tokens: '' temperature: 0.0 top_k: 0 top_p: 1.0 problem_type: text_causal_language_modeling tokenizer: add_prefix_space: false add_prompt_answer_tokens: false max_length: 800 max_length_answer: 32 max_length_prompt: 768 padding_quantile: 1.0 use_fast: true training: adaptive_kl_control: true advantages_gamma: 0.99 advantages_lambda: 0.95 batch_size: 4 differential_learning_rate: 1.0e-05 differential_learning_rate_layers: [] drop_last_batch: true epochs: 6 evaluate_before_training: false evaluation_epochs: 1.0 grad_accumulation: 1 gradient_clip: 0.1 initial_kl_coefficient: 0.2 kl_horizon: 10000 kl_target: 6.0 learning_rate: 0.0015 lora: true lora_alpha: 16 lora_dropout: 0.05 lora_r: 32 lora_target_modules: '' loss_function: TokenAveragedCrossEntropy offload_reward_model: false optimizer: AdamW ppo_batch_size: 1 ppo_clip_policy: 0.2 ppo_clip_value: 0.2 ppo_epochs: 4 ppo_generate_temperature: 1.0 reward_model: OpenAssistant/reward-model-deberta-v3-large-v2 save_best_checkpoint: false scaling_factor_value_loss: 0.1 schedule: Cosine train_validation_data: false use_rlhf: false warmup_epochs: 0.0 weight_decay: 0.0