{"args": {"dataset_name": "None", "dataset_train_split": "train", "dataset_test_split": "test", "sanity_check": false, "ignore_bias_buffers": false, "config": "None", "gradient_checkpointing_use_reentrant": false}, "training_args": {"output_dir": "/opt/dlami/nvme/output_dir/npo-HuggingFaceH4-zephyr-7b-beta-bio/20240902T231935", "overwrite_output_dir": false, "do_train": false, "do_eval": false, "do_predict": false, "eval_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 3, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 3, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 5e-05, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 150, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "runs/Sep02_23-19-35_ip-172-31-17-37", "logging_strategy": "steps", "logging_first_step": true, "logging_steps": 10, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 500, "save_total_limit": "None", "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 0, "ddp_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 100.0, "dataloader_num_workers": 0, "dataloader_prefetch_factor": "None", "past_index": -1, "run_name": "npo-zephyr-bio-20240902T231935", "disable_tqdm": false, "remove_unused_columns": false, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": "None", "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None)", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": "None", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "ddp_broadcast_buffers": "None", "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "None", "hub_strategy": "every_save", "hub_token": "None", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": "None", "include_inputs_for_metrics": false, "eval_do_concat_batches": true, "fp16_backend": "auto", "evaluation_strategy": "None", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "None", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": "None", "torch_compile_mode": "None", "dispatch_batches": "None", "split_batches": "None", "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": "None", "optim_target_modules": "None", "batch_eval_metrics": false, "beta": 0.1, "label_smoothing": 0, "loss_type": "sigmoid", "label_pad_token_id": -100, "padding_value": "None", "truncation_mode": "keep_end", "max_length": 1024, "max_prompt_length": 1024, "max_target_length": 1024, "is_encoder_decoder": "None", "disable_dropout": true, "generate_during_eval": false, "precompute_ref_log_probs": false, "dataset_num_proc": "None", "model_init_kwargs": "None", "ref_model_init_kwargs": "None", "model_adapter_name": "None", "ref_adapter_name": "None", "reference_free": false, "force_use_ref_model": false, "f_divergence_type": "FDivergenceType.REVERSE_KL", "f_alpha_divergence_coef": 1.0, "sync_ref_model": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "rpo_alpha": "None", "distributed_state": "Distributed environment: DistributedType.DEEPSPEED  Backend: nccl\nNum processes: 8\nProcess index: 0\nLocal process index: 0\nDevice: cuda:0\n", "_n_gpu": 1, "__cached__setup_devices": "cuda:0", "deepspeed_plugin": "DeepSpeedPlugin(hf_ds_config=<accelerate.utils.deepspeed.HfDeepSpeedConfig object at 0x7f4793d08470>, gradient_accumulation_steps='auto', gradient_clipping=1.0, zero_stage=3, is_train_batch_min=True, offload_optimizer_device='none', offload_param_device='none', offload_optimizer_nvme_path='none', offload_param_nvme_path='none', zero3_init_flag=True, zero3_save_16bit_model=True, transformer_moe_cls_names=None)"}, "model_config": {"model_name_or_path": "HuggingFaceH4/zephyr-7b-beta", "model_revision": "main", "torch_dtype": "None", "trust_remote_code": false, "attn_implementation": "None", "use_peft": false, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "lora_target_modules": "None", "lora_modules_to_save": "None", "lora_task_type": "CAUSAL_LM", "load_in_8bit": false, "load_in_4bit": false, "bnb_4bit_quant_type": "nf4", "use_bnb_nested_quant": false}, "exp_args": {"subset": "bio", "use_chat_template_p": 0.5, "retain_mult": 2.0}}