Arguments

class FlagEmbedding.finetune.embedder.encoder_only.m3.EncoderOnlyEmbedderM3ModelArguments(model_name_or_path: str, config_name: str = None, tokenizer_name: str = None, cache_dir: str = None, trust_remote_code: bool = False, use_fast_tokenizer: bool = True, token: str = <factory>, colbert_dim: int = -1)

Model argument class for M3.

class FlagEmbedding.finetune.embedder.encoder_only.m3.EncoderOnlyEmbedderM3TrainingArguments(output_dir: str | None = None, per_device_train_batch_size: int = 8, num_train_epochs: float = 3.0, max_steps: int = -1, learning_rate: float = 5e-05, lr_scheduler_type: SchedulerType | str = 'linear', lr_scheduler_kwargs: dict | str | None = None, warmup_steps: float = 0, optim: OptimizerNames | str = 'adamw_torch_fused', optim_args: str | None = None, weight_decay: float = 0.0, adam_beta1: float = 0.9, adam_beta2: float = 0.999, adam_epsilon: float = 1e-08, optim_target_modules: None | str | list[str] = None, gradient_accumulation_steps: int = 1, average_tokens_across_devices: bool = True, max_grad_norm: float = 1.0, label_smoothing_factor: float = 0.0, bf16: bool = False, fp16: bool = False, bf16_full_eval: bool = False, fp16_full_eval: bool = False, tf32: bool | None = None, gradient_checkpointing: bool = False, gradient_checkpointing_kwargs: dict[str, ~typing.Any] | str | None=None, torch_compile: bool = False, torch_compile_backend: str | None = None, torch_compile_mode: str | None = None, use_liger_kernel: bool = False, liger_kernel_config: dict[str, bool] | None=None, use_cache: bool = False, neftune_noise_alpha: float | None = None, torch_empty_cache_steps: int | None = None, auto_find_batch_size: bool = False, logging_strategy: IntervalStrategy | str = 'steps', logging_steps: float = 500, logging_first_step: bool = False, log_on_each_node: bool = True, logging_nan_inf_filter: bool = True, include_num_input_tokens_seen: str | bool = 'no', log_level: str = 'passive', log_level_replica: str = 'warning', disable_tqdm: bool | None = None, report_to: None | str | list[str] = 'none', run_name: str | None = None, project: str = 'huggingface', trackio_space_id: str | None = 'trackio', eval_strategy: IntervalStrategy | str = 'no', eval_steps: float | None = None, eval_delay: float = 0, per_device_eval_batch_size: int = 8, prediction_loss_only: bool = False, eval_on_start: bool = False, eval_do_concat_batches: bool = True, eval_use_gather_object: bool = False, eval_accumulation_steps: int | None = None, include_for_metrics: list[str] = <factory>, batch_eval_metrics: bool = False, save_only_model: bool = False, save_strategy: SaveStrategy | str = 'steps', save_steps: float = 500, save_on_each_node: bool = False, save_total_limit: int | None = None, enable_jit_checkpoint: bool = False, push_to_hub: bool = False, hub_token: str | None = None, hub_private_repo: bool | None = None, hub_model_id: str | None = None, hub_strategy: HubStrategy | str = 'every_save', hub_always_push: bool = False, hub_revision: str | None = None, load_best_model_at_end: bool = False, metric_for_best_model: str | None = None, greater_is_better: bool | None = None, ignore_data_skip: bool = False, restore_callback_states_from_checkpoint: bool = False, full_determinism: bool = False, seed: int = 42, data_seed: int | None = None, use_cpu: bool = False, accelerator_config: dict | str | None = None, parallelism_config: ParallelismConfig | None = None, dataloader_drop_last: bool = False, dataloader_num_workers: int = 0, dataloader_pin_memory: bool = True, dataloader_persistent_workers: bool = False, dataloader_prefetch_factor: int | None = None, remove_unused_columns: bool = True, label_names: list[str] | None = None, train_sampling_strategy: str = 'random', length_column_name: str = 'length', ddp_find_unused_parameters: bool | None = None, ddp_bucket_cap_mb: int | None = None, ddp_broadcast_buffers: bool | None = None, ddp_backend: str | None = None, ddp_timeout: int = 1800, fsdp: list[FSDPOption] | str | None = None, fsdp_config: dict[str, ~typing.Any] | str | None=None, deepspeed: dict | str | None = None, debug: str | list[DebugOption] = '', skip_memory_metrics: bool = True, do_train: bool = False, do_eval: bool = False, do_predict: bool = False, resume_from_checkpoint: str | None = None, warmup_ratio: float | None = None, logging_dir: str | None = None, local_rank: int = -1, negatives_cross_device: bool = False, temperature: float | None = 0.02, fix_position_embedding: bool = False, sentence_pooling_method: str = 'cls', normalize_embeddings: bool = True, sub_batch_size: int | None = None, kd_loss_type: str = 'kl_div', unified_finetuning: bool = False, use_self_distill: bool = False, fix_encoder: bool = False, self_distill_start_step: int = -1)

Training argument class for M3.