architecture: backbone_dtype: int4 force_embedding_gradients: false gradient_checkpointing: true intermediate_dropout: 0.0 pretrained: true pretrained_weights: /root/h2o-llmstudio/output/user/jasper-cicada.1/checkpoint.pth augmentation: neftune_noise_alpha: 0.0 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: assistant 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: parent_id personalize: false prompt_column: - user system_column: system text_answer_separator: <|answer|> text_prompt_start: <|prompt|> text_system_start: <|system|> train_dataframe: /root/h2o-llmstudio/data/user/task2_conversation_sp100v3/task2_conversation_sp100v3.parquet validation_dataframe: None validation_size: 0.01 validation_strategy: automatic environment: compile_model: false deepspeed_allgather_bucket_size: 1000000 deepspeed_method: ZeRO2 deepspeed_reduce_bucket_size: 1000000 deepspeed_stage3_param_persistence_threshold: 1000000 deepspeed_stage3_prefetch_bucket_size: 1000000 find_unused_parameters: false gpus: - '0' huggingface_branch: main mixed_precision: true mixed_precision_dtype: bfloat16 number_of_workers: 8 seed: -1 trust_remote_code: true use_deepspeed: false experiment_name: jasper-cicada.1.1 llm_backbone: google/gemma-1.1-2b-it logging: logger: None neptune_project: '' output_directory: /root/h2o-llmstudio/output/user/jasper-cicada.1.1/ prediction: batch_size_inference: 0 do_sample: false max_length_inference: 256 max_time: 0.0 metric: BLEU metric_gpt_model: gpt-3.5-turbo-0301 metric_gpt_template: general min_length_inference: 2 num_beams: 1 num_history: 4 repetition_penalty: 1.0 stop_tokens: '' temperature: 0.0 top_k: 0 top_p: 1.0 problem_type: text_causal_language_modeling tokenizer: add_prompt_answer_tokens: false max_length: 2080 max_length_answer: 3776 max_length_prompt: 1952 padding_quantile: 1.0 use_fast: true training: batch_size: 2 differential_learning_rate: 1.0e-05 differential_learning_rate_layers: [] drop_last_batch: true epochs: 1 evaluate_before_training: false evaluation_epochs: 1.0 grad_accumulation: 1 gradient_clip: 0.0 learning_rate: 0.0001 lora: true lora_alpha: 16 lora_dropout: 0.05 lora_r: 4 lora_target_modules: '' loss_function: TokenAveragedCrossEntropy optimizer: AdamW save_checkpoint: last schedule: Cosine train_validation_data: false use_flash_attention_2: false warmup_epochs: 0.0 weight_decay: 0.0